< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1633 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: 2.4780. Min Range: -2.4780

Max Act: 2.4780. Min Act: -0.1700

Data Index: 3076319 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.4003. Min Act: -0.1700

Data Index: 8493222 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3853. Min Act: -0.1700

Data Index: 7480145 (Open Web Text)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.4009. Min Act: -0.1700

Data Index: 5061876 (Open Web Text)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3688. Min Act: -0.1700

Data Index: 8607667 (Open Web Text)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3785. Min Act: -0.1700

Data Index: 2429685 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3599. Min Act: -0.1700

Data Index: 2447183 (Open Web Text)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3858. Min Act: -0.1700

Data Index: 5365727 (Open Web Text)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3636. Min Act: -0.1700

Data Index: 1203815 (Open Web Text)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3597. Min Act: -0.1700

Data Index: 6329475 (Open Web Text)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3378. Min Act: -0.1700

Data Index: 239610 (Open Web Text)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3552. Min Act: -0.1700

Data Index: 5999076 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3746. Min Act: -0.1700

Data Index: 3103061 (Open Web Text)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3555. Min Act: -0.1700

Data Index: 5745414 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3581. Min Act: -0.1700

Data Index: 5242248 (Open Web Text)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3528. Min Act: -0.1700

Data Index: 5705187 (Open Web Text)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3524. Min Act: -0.1700

Data Index: 5114257 (Open Web Text)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3266. Min Act: -0.1700

Data Index: 557175 (Open Web Text)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3455. Min Act: -0.1700

Data Index: 6917374 (Open Web Text)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4780. Min Range: -2.4780

Max Act: 2.3371. Min Act: -0.1700

Data Index: 4460774 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #19