Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1111 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0003

Data Index: 679676 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0306. Min Act: -0.0003

Data Index: 291597 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0302. Min Act: -0.0003

Data Index: 979328 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0293. Min Act: -0.0004

Data Index: 1019258 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0290. Min Act: -0.0003

Data Index: 458069 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0277. Min Act: -0.0003

Data Index: 276241 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1197805 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0270. Min Act: -0.0003

Data Index: 693178 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0279. Min Act: -0.0003

Data Index: 317771 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0276. Min Act: -0.0003

Data Index: 850958 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0267. Min Act: -0.0004

Data Index: 143520 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0274. Min Act: -0.0003

Data Index: 297382 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0272. Min Act: -0.0003

Data Index: 13993 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0259. Min Act: -0.0003

Data Index: 203300 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1027075 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0265. Min Act: -0.0003

Data Index: 532748 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0264. Min Act: -0.0004

Data Index: 1160440 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1254066 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0258. Min Act: -0.0003

Data Index: 654329 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0263. Min Act: -0.0002

Data Index: 540428 (C4 (Web Text))

Max Activating Token Index: 450