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

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

Neuron 591 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: 0.0198. Min Range: -0.0198

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1361986 (Python Code)

Max Activating Token Index: 387

Text #1

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1345504 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1295384 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1549093 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1055731 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0193. Min Act: -0.0006

Data Index: 434023 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0158. Min Act: -0.0006

Data Index: 798373 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1210273 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0157. Min Act: -0.0006

Data Index: 416957 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1402646 (Python Code)

Max Activating Token Index: 415

Text #10

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0183. Min Act: -0.0006

Data Index: 682841 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1100335 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1631430 (Python Code)

Max Activating Token Index: 377

Text #13

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1241868 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0161. Min Act: -0.0006

Data Index: 73220 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0142. Min Act: -0.0006

Data Index: 899836 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0144. Min Act: -0.0006

Data Index: 114373 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1375047 (Python Code)

Max Activating Token Index: 216

Text #18

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0140. Min Act: -0.0006

Data Index: 152568 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0164. Min Act: -0.0006

Data Index: 800631 (C4 (Web Text))

Max Activating Token Index: 80