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

Dataset: Open Web Text

Neuron 922 in Layer 1

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: 1.3878. Min Range: -1.3878

Max Act: 1.3878. Min Act: -0.1700

Data Index: 7085279 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3766. Min Act: -0.1699

Data Index: 2343804 (Open Web Text)

Max Activating Token Index: 131

Text #2

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3610. Min Act: -0.1700

Data Index: 6826566 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3475. Min Act: -0.1699

Data Index: 6744551 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3417. Min Act: -0.1697

Data Index: 5474432 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3388. Min Act: -0.1700

Data Index: 2077789 (Open Web Text)

Max Activating Token Index: 208

Text #6

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3259. Min Act: -0.1700

Data Index: 7024905 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3388. Min Act: -0.1700

Data Index: 8186578 (Open Web Text)

Max Activating Token Index: 575

Text #8

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3290. Min Act: -0.1700

Data Index: 3157115 (Open Web Text)

Max Activating Token Index: 358

Text #9

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3234. Min Act: -0.1690

Data Index: 5546667 (Open Web Text)

Max Activating Token Index: 253

Text #10

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3258. Min Act: -0.1700

Data Index: 1168215 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3212. Min Act: -0.1699

Data Index: 1328748 (Open Web Text)

Max Activating Token Index: 270

Text #12

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3195. Min Act: -0.1692

Data Index: 2273840 (Open Web Text)

Max Activating Token Index: 228

Text #13

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3214. Min Act: -0.1700

Data Index: 4404087 (Open Web Text)

Max Activating Token Index: 89

Text #14

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3226. Min Act: -0.1700

Data Index: 1377466 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3113. Min Act: -0.1700

Data Index: 5338130 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3153. Min Act: -0.1700

Data Index: 4261308 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3065. Min Act: -0.1673

Data Index: 250405 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3079. Min Act: -0.1699

Data Index: 5886853 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3176. Min Act: -0.1700

Data Index: 6120112 (Open Web Text)

Max Activating Token Index: 303