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

Dataset: Open Web Text

Neuron 2602 in Layer 4

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: 3.7957. Min Range: -3.7957

Max Act: 3.7957. Min Act: -0.1700

Data Index: 4820300 (Open Web Text)

Max Activating Token Index: 621

Text #1

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.7643. Min Act: -0.1700

Data Index: 5790732 (Open Web Text)

Max Activating Token Index: 239

Text #2

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.7519. Min Act: -0.1700

Data Index: 2234679 (Open Web Text)

Max Activating Token Index: 144

Text #3

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6455. Min Act: -0.1700

Data Index: 3084159 (Open Web Text)

Max Activating Token Index: 166

Text #4

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6233. Min Act: -0.1700

Data Index: 7995045 (Open Web Text)

Max Activating Token Index: 605

Text #5

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6378. Min Act: -0.1700

Data Index: 4750676 (Open Web Text)

Max Activating Token Index: 843

Text #6

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6276. Min Act: -0.1700

Data Index: 4691937 (Open Web Text)

Max Activating Token Index: 660

Text #7

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6145. Min Act: -0.1700

Data Index: 2207940 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5955. Min Act: -0.1700

Data Index: 8318696 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6003. Min Act: -0.1700

Data Index: 3207388 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5932. Min Act: -0.1700

Data Index: 4831821 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5628. Min Act: -0.1700

Data Index: 2549851 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5818. Min Act: -0.1700

Data Index: 4109834 (Open Web Text)

Max Activating Token Index: 825

Text #13

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5516. Min Act: -0.1700

Data Index: 2618939 (Open Web Text)

Max Activating Token Index: 82

Text #14

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5692. Min Act: -0.1700

Data Index: 6023605 (Open Web Text)

Max Activating Token Index: 867

Text #15

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5385. Min Act: -0.1700

Data Index: 8107464 (Open Web Text)

Max Activating Token Index: 979

Text #16

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5271. Min Act: -0.1700

Data Index: 6278191 (Open Web Text)

Max Activating Token Index: 279

Text #17

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5188. Min Act: -0.1700

Data Index: 6035534 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5298. Min Act: -0.1700

Data Index: 147733 (Open Web Text)

Max Activating Token Index: 672

Text #19

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4929. Min Act: -0.1700

Data Index: 7951828 (Open Web Text)

Max Activating Token Index: 886