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

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

Neuron 1184 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0006

Data Index: 903926 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0290. Min Act: -0.0006

Data Index: 466945 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0282. Min Act: -0.0006

Data Index: 700248 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0278. Min Act: -0.0006

Data Index: 362408 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0284. Min Act: -0.0005

Data Index: 1287489 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0276. Min Act: -0.0006

Data Index: 823741 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0270. Min Act: -0.0006

Data Index: 27435 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0274. Min Act: -0.0006

Data Index: 271647 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1139036 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1056877 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0271. Min Act: -0.0006

Data Index: 988710 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0258. Min Act: -0.0006

Data Index: 1061352 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0263. Min Act: -0.0006

Data Index: 256802 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0250. Min Act: -0.0006

Data Index: 29572 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0258. Min Act: -0.0006

Data Index: 1144611 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0262. Min Act: -0.0006

Data Index: 876379 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0262. Min Act: -0.0006

Data Index: 11070 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0255. Min Act: -0.0006

Data Index: 846686 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0256. Min Act: -0.0006

Data Index: 359347 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0256. Min Act: -0.0006

Data Index: 432404 (C4 (Web Text))

Max Activating Token Index: 879