Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.9148. Min Act: -0.0000

Data Index: 372389 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7312. Min Act: -0.0000

Data Index: 1111559 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7356. Min Act: -0.0000

Data Index: 1183575 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.6889. Min Act: -0.0000

Data Index: 518989 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.6434. Min Act: -0.0000

Data Index: 777459 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.6264. Min Act: -0.0000

Data Index: 182245 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.5524. Min Act: -0.0000

Data Index: 289238 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.4780. Min Act: -0.0000

Data Index: 890492 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.6016. Min Act: -0.0000

Data Index: 634994 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1339355 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.4451. Min Act: -0.0000

Data Index: 648449 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.3727. Min Act: -0.0000

Data Index: 274902 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.4206. Min Act: -0.0000

Data Index: 837075 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.3998. Min Act: -0.0000

Data Index: 592441 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1095101 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.3190. Min Act: -0.0000

Data Index: 173019 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.4196. Min Act: -0.0000

Data Index: 554087 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1197823 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.3669. Min Act: -0.0000

Data Index: 202173 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.3699. Min Act: -0.0000

Data Index: 1255932 (C4 (Web Text))

Max Activating Token Index: 651