Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3647 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0198. Min Act: -0.0003

Data Index: 919179 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0187. Min Act: -0.0003

Data Index: 1257932 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1231092 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0178. Min Act: -0.0003

Data Index: 980435 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0176. Min Act: -0.0003

Data Index: 471490 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0176. Min Act: -0.0003

Data Index: 73089 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0171. Min Act: -0.0003

Data Index: 261311 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1156624 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0165. Min Act: -0.0003

Data Index: 237251 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0164. Min Act: -0.0003

Data Index: 685383 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1330071 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0163. Min Act: -0.0003

Data Index: 394815 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0162. Min Act: -0.0003

Data Index: 201127 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1007586 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0161. Min Act: -0.0003

Data Index: 684577 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0164. Min Act: -0.0003

Data Index: 125384 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0161. Min Act: -0.0003

Data Index: 25786 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0160. Min Act: -0.0003

Data Index: 979164 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1286737 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0156. Min Act: -0.0003

Data Index: 129831 (C4 (Web Text))

Max Activating Token Index: 728