Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1666 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0180. Min Act: -0.0006

Data Index: 450787 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0179. Min Act: -0.0006

Data Index: 362572 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0175. Min Act: -0.0006

Data Index: 341121 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0176. Min Act: -0.0006

Data Index: 244153 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0176. Min Act: -0.0006

Data Index: 373038 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1101047 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1171673 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1001945 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0165. Min Act: -0.0006

Data Index: 807205 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0173. Min Act: -0.0006

Data Index: 954140 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0164. Min Act: -0.0006

Data Index: 910541 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0167. Min Act: -0.0006

Data Index: 760704 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0167. Min Act: -0.0006

Data Index: 624823 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0167. Min Act: -0.0005

Data Index: 1134271 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0167. Min Act: -0.0006

Data Index: 10022 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0159. Min Act: -0.0006

Data Index: 255214 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0165. Min Act: -0.0005

Data Index: 290114 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1097247 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1022301 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0158. Min Act: -0.0006

Data Index: 677787 (C4 (Web Text))

Max Activating Token Index: 211