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

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

Neuron 642 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0006

Data Index: 71091 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1198283 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0255. Min Act: -0.0006

Data Index: 752950 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0255. Min Act: -0.0007

Data Index: 815679 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0243. Min Act: -0.0006

Data Index: 170845 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0239. Min Act: -0.0006

Data Index: 575631 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0240. Min Act: -0.0006

Data Index: 710347 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0233. Min Act: -0.0006

Data Index: 4606 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1308400 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0006

Data Index: 639912 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0228. Min Act: -0.0006

Data Index: 157747 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0227. Min Act: -0.0006

Data Index: 733104 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0221. Min Act: -0.0006

Data Index: 315088 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0221. Min Act: -0.0006

Data Index: 475983 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0229. Min Act: -0.0006

Data Index: 677433 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0228. Min Act: -0.0006

Data Index: 536842 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0229. Min Act: -0.0006

Data Index: 526233 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0223. Min Act: -0.0006

Data Index: 901241 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0223. Min Act: -0.0006

Data Index: 353106 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0222. Min Act: -0.0007

Data Index: 1272012 (C4 (Web Text))

Max Activating Token Index: 305