Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1054 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0317. Min Act: -0.0006

Data Index: 656458 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1288004 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0006

Data Index: 37719 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0283. Min Act: -0.0006

Data Index: 903629 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0293. Min Act: -0.0006

Data Index: 832194 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0286. Min Act: -0.0006

Data Index: 12029 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1027203 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0268. Min Act: -0.0006

Data Index: 357759 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0289. Min Act: -0.0006

Data Index: 739471 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0290. Min Act: -0.0006

Data Index: 998944 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0268. Min Act: -0.0006

Data Index: 670656 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0260. Min Act: -0.0006

Data Index: 391975 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1034517 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1296939 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0273. Min Act: -0.0006

Data Index: 759691 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0272. Min Act: -0.0006

Data Index: 338861 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0273. Min Act: -0.0006

Data Index: 832897 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0270. Min Act: -0.0006

Data Index: 656821 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1275047 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0264. Min Act: -0.0006

Data Index: 1269264 (C4 (Web Text))

Max Activating Token Index: 168