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

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

Neuron 2581 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1380030 (Python Code)

Max Activating Token Index: 765

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0260. Min Act: -0.0002

Data Index: 63557 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0253. Min Act: -0.0002

Data Index: 395981 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0251. Min Act: -0.0002

Data Index: 890353 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1230558 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1216012 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1523314 (Python Code)

Max Activating Token Index: 998

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1399951 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0228. Min Act: -0.0002

Data Index: 984242 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0215. Min Act: -0.0002

Data Index: 580195 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1339527 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1320617 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0216. Min Act: -0.0002

Data Index: 209649 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0209. Min Act: -0.0002

Data Index: 613594 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0201. Min Act: -0.0002

Data Index: 75140 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0206. Min Act: -0.0002

Data Index: 840332 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0205. Min Act: -0.0002

Data Index: 467835 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1372039 (Python Code)

Max Activating Token Index: 655

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1373477 (Python Code)

Max Activating Token Index: 434

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1188073 (C4 (Web Text))

Max Activating Token Index: 785