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

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

Neuron 2974 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3358. Min Range: -1.3358

Max Act: 1.0225. Min Act: -0.0003

Data Index: 485910 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7241. Min Act: -0.0003

Data Index: 655055 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8158. Min Act: -0.0003

Data Index: 1016883 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7637. Min Act: -0.0003

Data Index: 623999 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9003. Min Act: -0.0004

Data Index: 1276953 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.4919. Min Act: -0.0003

Data Index: 1227933 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9194. Min Act: -0.0003

Data Index: 968836 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9473. Min Act: -0.0003

Data Index: 124057 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.3358. Min Range: -1.3358

Max Act: 1.3358. Min Act: -0.0003

Data Index: 287760 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8122. Min Act: -0.0003

Data Index: 605658 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8607. Min Act: -0.0003

Data Index: 574454 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9638. Min Act: -0.0003

Data Index: 360762 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8217. Min Act: -0.0003

Data Index: 97499 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9265. Min Act: -0.0003

Data Index: 1123285 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8015. Min Act: -0.0003

Data Index: 910506 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9860. Min Act: -0.0003

Data Index: 1108462 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9258. Min Act: -0.0003

Data Index: 617557 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7708. Min Act: -0.0003

Data Index: 1298352 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8658. Min Act: -0.0003

Data Index: 954540 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9200. Min Act: -0.0003

Data Index: 325559 (C4 (Web Text))

Max Activating Token Index: 431