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

Dataset: Open Web Text

Neuron 631 in Layer 3

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: 4.8695. Min Range: -4.8695

Max Act: 4.8695. Min Act: -0.1700

Data Index: 2888914 (Open Web Text)

Max Activating Token Index: 305

Text #1

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.8397. Min Act: -0.1700

Data Index: 1696523 (Open Web Text)

Max Activating Token Index: 255

Text #2

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.8016. Min Act: -0.1700

Data Index: 5003862 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.8082. Min Act: -0.1700

Data Index: 4306784 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.7540. Min Act: -0.1700

Data Index: 6228832 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.7067. Min Act: -0.1700

Data Index: 6073730 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.7041. Min Act: -0.1700

Data Index: 8795829 (Open Web Text)

Max Activating Token Index: 491

Text #7

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.7229. Min Act: -0.1700

Data Index: 1065851 (Open Web Text)

Max Activating Token Index: 230

Text #8

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.7257. Min Act: -0.1700

Data Index: 577118 (Open Web Text)

Max Activating Token Index: 307

Text #9

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6752. Min Act: -0.1700

Data Index: 5624446 (Open Web Text)

Max Activating Token Index: 460

Text #10

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6768. Min Act: -0.1700

Data Index: 7431674 (Open Web Text)

Max Activating Token Index: 700

Text #11

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6640. Min Act: -0.1700

Data Index: 4370644 (Open Web Text)

Max Activating Token Index: 649

Text #12

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6583. Min Act: -0.1700

Data Index: 3496953 (Open Web Text)

Max Activating Token Index: 696

Text #13

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6464. Min Act: -0.1700

Data Index: 1815306 (Open Web Text)

Max Activating Token Index: 511

Text #14

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6438. Min Act: -0.1700

Data Index: 7035468 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6461. Min Act: -0.1700

Data Index: 7159754 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6276. Min Act: -0.1700

Data Index: 3325245 (Open Web Text)

Max Activating Token Index: 819

Text #17

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6174. Min Act: -0.1700

Data Index: 2964986 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6098. Min Act: -0.1700

Data Index: 229539 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5756. Min Act: -0.1700

Data Index: 1831078 (Open Web Text)

Max Activating Token Index: 579