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

Dataset: Open Web Text

Neuron 2036 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: 4.9651. Min Range: -4.9651

Max Act: 4.9651. Min Act: -0.1700

Data Index: 4178004 (Open Web Text)

Max Activating Token Index: 156

Text #1

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.9607. Min Act: -0.1700

Data Index: 3873843 (Open Web Text)

Max Activating Token Index: 426

Text #2

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.8811. Min Act: -0.1700

Data Index: 5994946 (Open Web Text)

Max Activating Token Index: 167

Text #3

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.8409. Min Act: -0.1700

Data Index: 6115555 (Open Web Text)

Max Activating Token Index: 836

Text #4

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.8597. Min Act: -0.1700

Data Index: 5535902 (Open Web Text)

Max Activating Token Index: 44

Text #5

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.8216. Min Act: -0.1700

Data Index: 1090049 (Open Web Text)

Max Activating Token Index: 170

Text #6

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7809. Min Act: -0.1700

Data Index: 7296438 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.8156. Min Act: -0.1700

Data Index: 4699951 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7902. Min Act: -0.1700

Data Index: 7065673 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7331. Min Act: -0.1700

Data Index: 3562025 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7411. Min Act: -0.1700

Data Index: 2644108 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7716. Min Act: -0.1700

Data Index: 2535596 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7279. Min Act: -0.1700

Data Index: 8428262 (Open Web Text)

Max Activating Token Index: 437

Text #13

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7621. Min Act: -0.1700

Data Index: 6163566 (Open Web Text)

Max Activating Token Index: 252

Text #14

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7220. Min Act: -0.1700

Data Index: 5299782 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7120. Min Act: -0.1700

Data Index: 4274324 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7338. Min Act: -0.1700

Data Index: 3426436 (Open Web Text)

Max Activating Token Index: 220

Text #17

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7210. Min Act: -0.1700

Data Index: 3521132 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.6965. Min Act: -0.1700

Data Index: 8364490 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 4.9651. Min Range: -4.9651

Max Act: 4.7007. Min Act: -0.1700

Data Index: 3066469 (Open Web Text)

Max Activating Token Index: 1017