Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 703 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0006

Data Index: 331820 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1057621 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1047561 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1127950 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0245. Min Act: -0.0006

Data Index: 57785 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0262. Min Act: -0.0006

Data Index: 880291 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1169312 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0244. Min Act: -0.0006

Data Index: 567456 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0266. Min Act: -0.0006

Data Index: 965204 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0251. Min Act: -0.0006

Data Index: 487110 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1333730 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0244. Min Act: -0.0006

Data Index: 933247 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0263. Min Act: -0.0006

Data Index: 771503 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0235. Min Act: -0.0006

Data Index: 520195 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0235. Min Act: -0.0006

Data Index: 890311 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1165952 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0245. Min Act: -0.0006

Data Index: 10774 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0238. Min Act: -0.0006

Data Index: 281740 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0244. Min Act: -0.0006

Data Index: 475631 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1318767 (C4 (Web Text))

Max Activating Token Index: 962