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

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

Neuron 4834 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: 0.0213. Min Range: -0.0213

Max Act: 0.0213. Min Act: -0.0002

Data Index: 652371 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0159. Min Act: -0.0002

Data Index: 429680 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0156. Min Act: -0.0002

Data Index: 367622 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0193. Min Act: -0.0002

Data Index: 86041 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0163. Min Act: -0.0002

Data Index: 340640 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1276601 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1073616 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0179. Min Act: -0.0002

Data Index: 969243 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0163. Min Act: -0.0002

Data Index: 420767 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0165. Min Act: -0.0002

Data Index: 189064 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0182. Min Act: -0.0002

Data Index: 187040 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1611732 (Python Code)

Max Activating Token Index: 835

Text #12

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0174. Min Act: -0.0002

Data Index: 209945 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0174. Min Act: -0.0002

Data Index: 646932 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0196. Min Act: -0.0002

Data Index: 191662 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0174. Min Act: -0.0002

Data Index: 73679 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0144. Min Act: -0.0002

Data Index: 337856 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1284275 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0179. Min Act: -0.0002

Data Index: 344859 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1143139 (C4 (Web Text))

Max Activating Token Index: 310