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

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

Neuron 1106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1144. Min Act: -0.0003

Data Index: 1368902 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1156. Min Act: -0.0003

Data Index: 1520653 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1105. Min Act: -0.0003

Data Index: 1276388 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1134. Min Act: -0.0003

Data Index: 587671 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1196. Min Act: -0.0003

Data Index: 595762 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1123. Min Act: -0.0003

Data Index: 990605 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1064. Min Act: -0.0002

Data Index: 748595 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1070. Min Act: -0.0003

Data Index: 362149 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1061. Min Act: -0.0003

Data Index: 499901 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1044. Min Act: -0.0003

Data Index: 874772 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1039. Min Act: -0.0003

Data Index: 309956 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1080. Min Act: -0.0003

Data Index: 849542 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1064. Min Act: -0.0003

Data Index: 1290889 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1053. Min Act: -0.0003

Data Index: 1276469 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1027. Min Act: -0.0003

Data Index: 484628 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1002. Min Act: -0.0003

Data Index: 1575529 (Python Code)

Max Activating Token Index: 372

Text #16

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1056. Min Act: -0.0003

Data Index: 1565838 (Python Code)

Max Activating Token Index: 530

Text #17

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1627347 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0968. Min Act: -0.0002

Data Index: 427454 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0958. Min Act: -0.0003

Data Index: 1279093 (C4 (Web Text))

Max Activating Token Index: 574