Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1850 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0003

Data Index: 59792 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0332. Min Act: -0.0002

Data Index: 553978 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1228913 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0317. Min Act: -0.0002

Data Index: 985167 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0305. Min Act: -0.0002

Data Index: 978164 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0302. Min Act: -0.0003

Data Index: 421178 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0297. Min Act: -0.0003

Data Index: 290453 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0293. Min Act: -0.0003

Data Index: 7076 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0291. Min Act: -0.0002

Data Index: 313260 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0286. Min Act: -0.0003

Data Index: 662360 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0287. Min Act: -0.0001

Data Index: 173133 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0284. Min Act: -0.0003

Data Index: 596515 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0279. Min Act: -0.0002

Data Index: 934227 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0291. Min Act: -0.0001

Data Index: 967460 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0277. Min Act: -0.0003

Data Index: 295662 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1087928 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0276. Min Act: -0.0003

Data Index: 368367 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1029730 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0274. Min Act: -0.0002

Data Index: 743329 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0272. Min Act: -0.0002

Data Index: 982313 (C4 (Web Text))

Max Activating Token Index: 83