Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4250 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.8156. Min Act: -0.0003

Data Index: 264365 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7873. Min Act: -0.0002

Data Index: 806953 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7317. Min Act: -0.0002

Data Index: 1330590 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7272. Min Act: -0.0002

Data Index: 1254971 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6957. Min Act: -0.0002

Data Index: 1208730 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6760. Min Act: -0.0002

Data Index: 1107502 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6701. Min Act: -0.0003

Data Index: 516619 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6618. Min Act: -0.0003

Data Index: 608038 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6548. Min Act: -0.0003

Data Index: 366545 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6620. Min Act: -0.0002

Data Index: 1337232 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6586. Min Act: -0.0002

Data Index: 921369 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6548. Min Act: -0.0003

Data Index: 795101 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6446. Min Act: -0.0002

Data Index: 1284950 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6377. Min Act: -0.0003

Data Index: 202828 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6364. Min Act: -0.0002

Data Index: 279954 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6229. Min Act: -0.0002

Data Index: 581491 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6286. Min Act: -0.0002

Data Index: 525354 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6165. Min Act: -0.0002

Data Index: 402529 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6219. Min Act: -0.0003

Data Index: 1044374 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6144. Min Act: -0.0002

Data Index: 821038 (C4 (Web Text))

Max Activating Token Index: 230