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

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

Neuron 1917 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0002

Data Index: 808097 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0217. Min Act: -0.0002

Data Index: 59137 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0211. Min Act: -0.0002

Data Index: 772298 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0211. Min Act: -0.0002

Data Index: 236978 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0208. Min Act: -0.0002

Data Index: 988150 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0207. Min Act: -0.0002

Data Index: 659083 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0206. Min Act: -0.0002

Data Index: 940257 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1354296 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0204. Min Act: -0.0002

Data Index: 122082 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0204. Min Act: -0.0002

Data Index: 506288 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0202. Min Act: -0.0002

Data Index: 468564 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0202. Min Act: -0.0002

Data Index: 721156 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1391093 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1169512 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0199. Min Act: -0.0002

Data Index: 702742 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1166843 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0199. Min Act: -0.0002

Data Index: 349122 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0002

Data Index: 438810 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0202. Min Act: -0.0001

Data Index: 484091 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0002

Data Index: 886459 (C4 (Web Text))

Max Activating Token Index: 772