Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 262 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0004

Data Index: 609704 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0266. Min Act: -0.0004

Data Index: 1454807 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0258. Min Act: -0.0004

Data Index: 951208 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0263. Min Act: -0.0004

Data Index: 406170 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0257. Min Act: -0.0005

Data Index: 279636 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1110734 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1600220 (Python Code)

Max Activating Token Index: 262

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0245. Min Act: -0.0004

Data Index: 596277 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0243. Min Act: -0.0004

Data Index: 899776 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0242. Min Act: -0.0004

Data Index: 299832 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0245. Min Act: -0.0004

Data Index: 997776 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0245. Min Act: -0.0004

Data Index: 650089 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0250. Min Act: -0.0004

Data Index: 561317 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0241. Min Act: -0.0004

Data Index: 1164915 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1233253 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0238. Min Act: -0.0004

Data Index: 393008 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1004071 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1257238 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0243. Min Act: -0.0004

Data Index: 948245 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0243. Min Act: -0.0004

Data Index: 598684 (C4 (Web Text))

Max Activating Token Index: 349