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

Dataset: Open Web Text

Neuron 687 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: 3.8824. Min Range: -3.8824

Max Act: 3.8824. Min Act: -0.1700

Data Index: 7542102 (Open Web Text)

Max Activating Token Index: 235

Text #1

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.8256. Min Act: -0.1700

Data Index: 5327559 (Open Web Text)

Max Activating Token Index: 992

Text #2

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.8246. Min Act: -0.1700

Data Index: 1053309 (Open Web Text)

Max Activating Token Index: 107

Text #3

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.8561. Min Act: -0.1700

Data Index: 5180334 (Open Web Text)

Max Activating Token Index: 824

Text #4

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.8096. Min Act: -0.1700

Data Index: 6987802 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.8150. Min Act: -0.1700

Data Index: 3183385 (Open Web Text)

Max Activating Token Index: 225

Text #6

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.8043. Min Act: -0.1700

Data Index: 823428 (Open Web Text)

Max Activating Token Index: 404

Text #7

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7623. Min Act: -0.1700

Data Index: 8696645 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7936. Min Act: -0.1700

Data Index: 6767140 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7524. Min Act: -0.1700

Data Index: 5846764 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7549. Min Act: -0.1700

Data Index: 7282167 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7434. Min Act: -0.1700

Data Index: 7190133 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7625. Min Act: -0.1700

Data Index: 2868428 (Open Web Text)

Max Activating Token Index: 987

Text #13

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7344. Min Act: -0.1700

Data Index: 6931580 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7325. Min Act: -0.1700

Data Index: 5500441 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7025. Min Act: -0.1700

Data Index: 3253440 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7210. Min Act: -0.1700

Data Index: 5070266 (Open Web Text)

Max Activating Token Index: 100

Text #17

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7003. Min Act: -0.1700

Data Index: 7664231 (Open Web Text)

Max Activating Token Index: 215

Text #18

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7135. Min Act: -0.1700

Data Index: 2204943 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7160. Min Act: -0.1700

Data Index: 5237745 (Open Web Text)

Max Activating Token Index: 828