Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 442 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0006

Data Index: 271000 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1079413 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0158. Min Act: -0.0005

Data Index: 24024 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0161. Min Act: -0.0006

Data Index: 77917 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0163. Min Act: -0.0006

Data Index: 645631 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1324323 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0152. Min Act: -0.0005

Data Index: 1048345 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1352496 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0154. Min Act: -0.0006

Data Index: 516910 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0153. Min Act: -0.0006

Data Index: 530329 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0152. Min Act: -0.0005

Data Index: 830025 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1351823 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0149. Min Act: -0.0006

Data Index: 357488 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0152. Min Act: -0.0005

Data Index: 386235 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1211726 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0151. Min Act: -0.0006

Data Index: 652171 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0150. Min Act: -0.0006

Data Index: 483972 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0147. Min Act: -0.0005

Data Index: 190431 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1131292 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1114662 (C4 (Web Text))

Max Activating Token Index: 643