Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1255 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 305362 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0327. Min Act: -0.0003

Data Index: 917370 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1310286 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0284. Min Act: -0.0004

Data Index: 904693 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0270. Min Act: -0.0003

Data Index: 768067 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1179424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1201386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1204104 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1140621 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0211. Min Act: -0.0003

Data Index: 586357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0210. Min Act: -0.0004

Data Index: 385987 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0205. Min Act: -0.0004

Data Index: 418076 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0203. Min Act: -0.0003

Data Index: 80324 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0202. Min Act: -0.0003

Data Index: 368368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1569895 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0192. Min Act: -0.0003

Data Index: 378557 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0191. Min Act: -0.0003

Data Index: 461091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0183. Min Act: -0.0003

Data Index: 397608 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0183. Min Act: -0.0003

Data Index: 746048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0179. Min Act: -0.0003

Data Index: 844683 (C4 (Web Text))

Max Activating Token Index: 1023