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

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

Neuron 3432 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1859. Min Act: -0.0002

Data Index: 746724 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1513. Min Act: -0.0002

Data Index: 545953 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1573. Min Act: -0.0002

Data Index: 641820 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1493. Min Act: -0.0002

Data Index: 462231 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1372. Min Act: -0.0002

Data Index: 89817 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1307. Min Act: -0.0002

Data Index: 252485 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1239. Min Act: -0.0001

Data Index: 210223 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1327. Min Act: -0.0002

Data Index: 736059 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1220. Min Act: -0.0002

Data Index: 591510 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1250. Min Act: -0.0001

Data Index: 704602 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1245. Min Act: -0.0002

Data Index: 301011 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1229. Min Act: -0.0002

Data Index: 848716 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1047. Min Act: -0.0002

Data Index: 522660 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1178. Min Act: -0.0002

Data Index: 857486 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1226139 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1132. Min Act: -0.0002

Data Index: 67489 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1031433 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1118. Min Act: -0.0001

Data Index: 245497 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1027073 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.0991. Min Act: -0.0002

Data Index: 480776 (C4 (Web Text))

Max Activating Token Index: 926