< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2184 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.4732. Min Act: -0.1700

Data Index: 7971731 (Open Web Text)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.4371. Min Act: -0.1700

Data Index: 3583195 (Open Web Text)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.4010. Min Act: -0.1700

Data Index: 8070392 (Open Web Text)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.4134. Min Act: -0.1700

Data Index: 3625719 (Open Web Text)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.3798. Min Act: -0.1700

Data Index: 2064979 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2978. Min Act: -0.1700

Data Index: 4324223 (Open Web Text)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2707. Min Act: -0.1700

Data Index: 3035847 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2823. Min Act: -0.1700

Data Index: 1213826 (Open Web Text)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2869. Min Act: -0.1700

Data Index: 5123302 (Open Web Text)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.3041. Min Act: -0.1700

Data Index: 6539513 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2872. Min Act: -0.1700

Data Index: 190039 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2715. Min Act: -0.1700

Data Index: 7446968 (Open Web Text)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2540. Min Act: -0.1700

Data Index: 2697990 (Open Web Text)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2634. Min Act: -0.1700

Data Index: 8195225 (Open Web Text)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2499. Min Act: -0.1700

Data Index: 6859593 (Open Web Text)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2867. Min Act: -0.1700

Data Index: 8177533 (Open Web Text)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2750. Min Act: -0.1700

Data Index: 3532634 (Open Web Text)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2587. Min Act: -0.1700

Data Index: 4554923 (Open Web Text)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2198. Min Act: -0.1700

Data Index: 2674195 (Open Web Text)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.4732. Min Range: -4.4732

Max Act: 4.2346. Min Act: -0.1700

Data Index: 7258356 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #19