Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4163 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0361. Min Act: -0.0003

Data Index: 914848 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1217949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0316. Min Act: -0.0003

Data Index: 503440 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0329. Min Act: -0.0003

Data Index: 300160 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0293. Min Act: -0.0003

Data Index: 230748 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1038172 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1265442 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1246683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0304. Min Act: -0.0003

Data Index: 151190 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0308. Min Act: -0.0003

Data Index: 509030 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0292. Min Act: -0.0003

Data Index: 297620 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1005813 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0288. Min Act: -0.0003

Data Index: 893020 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0287. Min Act: -0.0003

Data Index: 298622 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1354276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0271. Min Act: -0.0003

Data Index: 806296 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0307. Min Act: -0.0003

Data Index: 426515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0284. Min Act: -0.0003

Data Index: 732927 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0297. Min Act: -0.0003

Data Index: 928448 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0255. Min Act: -0.0003

Data Index: 458118 (C4 (Web Text))

Max Activating Token Index: 772