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

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

Neuron 1998 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1181170 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0169. Min Act: -0.0002

Data Index: 450607 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0177. Min Act: -0.0002

Data Index: 182215 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0150. Min Act: -0.0002

Data Index: 786187 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0166. Min Act: -0.0002

Data Index: 248148 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0142. Min Act: -0.0002

Data Index: 828518 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0182. Min Act: -0.0002

Data Index: 284883 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0152. Min Act: -0.0002

Data Index: 320726 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0176. Min Act: -0.0002

Data Index: 503924 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0157. Min Act: -0.0002

Data Index: 436649 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1240144 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0142. Min Act: -0.0002

Data Index: 617428 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0155. Min Act: -0.0002

Data Index: 517067 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0150. Min Act: -0.0002

Data Index: 119808 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0144. Min Act: -0.0002

Data Index: 383960 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0134. Min Act: -0.0002

Data Index: 67793 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1473094 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0125. Min Act: -0.0002

Data Index: 955729 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0101. Min Act: -0.0002

Data Index: 547767 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0097. Min Act: -0.0002

Data Index: 423311 (C4 (Web Text))

Max Activating Token Index: 611