< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1984 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 16.4868. Min Range: -16.4868

Max Act: 16.3156. Min Act: -0.1700

Data Index: 4147588 (Open Web Text)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 16.4868. Min Range: -16.4868

Max Act: 16.4868. Min Act: -0.1700

Data Index: 5936973 (Open Web Text)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 16.4868. Min Range: -16.4868

Max Act: 16.1939. Min Act: -0.1700

Data Index: 4164808 (Open Web Text)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 16.4868. Min Range: -16.4868

Max Act: 16.0486. Min Act: -0.1700

Data Index: 6319192 (Open Web Text)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.9617. Min Act: -0.1700

Data Index: 1767087 (Open Web Text)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.7737. Min Act: -0.1700

Data Index: 4122827 (Open Web Text)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.7544. Min Act: -0.1700

Data Index: 6602869 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.7254. Min Act: -0.1700

Data Index: 6019842 (Open Web Text)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.5005. Min Act: -0.1700

Data Index: 5841469 (Open Web Text)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.4692. Min Act: -0.1700

Data Index: 3386324 (Open Web Text)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.4737. Min Act: -0.1700

Data Index: 1155593 (Open Web Text)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.5595. Min Act: -0.1700

Data Index: 4563521 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.4073. Min Act: -0.1700

Data Index: 477665 (Open Web Text)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.4726. Min Act: -0.1700

Data Index: 2670317 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.4960. Min Act: -0.1700

Data Index: 8342025 (Open Web Text)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.3965. Min Act: -0.1700

Data Index: 5769218 (Open Web Text)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.4170. Min Act: -0.1700

Data Index: 3014667 (Open Web Text)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.3445. Min Act: -0.1700

Data Index: 4286739 (Open Web Text)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.2339. Min Act: -0.1700

Data Index: 1828949 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 16.4868. Min Range: -16.4868

Max Act: 15.2540. Min Act: -0.1700

Data Index: 3903898 (Open Web Text)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #19