< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1465 in Layer 2

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: 4.9224. Min Range: -4.9224

Max Act: 4.9224. Min Act: -0.1700

Data Index: 7612068 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.9092. Min Act: -0.1700

Data Index: 8013207 (Open Web Text)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.8729. Min Act: -0.1700

Data Index: 8585354 (Open Web Text)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.8821. Min Act: -0.1700

Data Index: 6482717 (Open Web Text)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.8478. Min Act: -0.1700

Data Index: 3747679 (Open Web Text)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.8397. Min Act: -0.1700

Data Index: 859609 (Open Web Text)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7808. Min Act: -0.1700

Data Index: 6482715 (Open Web Text)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7641. Min Act: -0.1700

Data Index: 1593584 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7452. Min Act: -0.1700

Data Index: 8776756 (Open Web Text)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7333. Min Act: -0.1700

Data Index: 8777607 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7592. Min Act: -0.1700

Data Index: 1367777 (Open Web Text)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7320. Min Act: -0.1700

Data Index: 530579 (Open Web Text)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7165. Min Act: -0.1700

Data Index: 7533284 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7147. Min Act: -0.1700

Data Index: 7403772 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.6934. Min Act: -0.1700

Data Index: 6778732 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7144. Min Act: -0.1700

Data Index: 1642054 (Open Web Text)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7008. Min Act: -0.1700

Data Index: 6369557 (Open Web Text)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7050. Min Act: -0.1700

Data Index: 530581 (Open Web Text)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.6899. Min Act: -0.1700

Data Index: 4508005 (Open Web Text)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.9224. Min Range: -4.9224

Max Act: 4.7043. Min Act: -0.1700

Data Index: 726737 (Open Web Text)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #19