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

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

Neuron 3260 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: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0003

Data Index: 779004 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1145325 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 313946 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 163854 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1099812 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0164. Min Act: -0.0003

Data Index: 168966 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1064613 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0159. Min Act: -0.0003

Data Index: 155815 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 274646 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 121322 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0159. Min Act: -0.0003

Data Index: 869226 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0165. Min Act: -0.0003

Data Index: 374127 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1101199 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 175791 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 857465 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 507235 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 35731 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 49489 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1315116 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1011928 (C4 (Web Text))

Max Activating Token Index: 884