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

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

Neuron 2527 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: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0002

Data Index: 668035 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0330. Min Act: -0.0002

Data Index: 969034 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1229908 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0311. Min Act: -0.0001

Data Index: 169420 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0308. Min Act: -0.0001

Data Index: 640368 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0297. Min Act: -0.0002

Data Index: 72444 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0292. Min Act: -0.0002

Data Index: 178268 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1025706 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0287. Min Act: -0.0002

Data Index: 138887 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0285. Min Act: -0.0002

Data Index: 274553 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0283. Min Act: -0.0002

Data Index: 623889 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0284. Min Act: -0.0002

Data Index: 425796 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1145400 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0276. Min Act: -0.0001

Data Index: 553757 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0274. Min Act: -0.0002

Data Index: 142237 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0272. Min Act: -0.0002

Data Index: 170358 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0271. Min Act: -0.0002

Data Index: 788557 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0270. Min Act: -0.0002

Data Index: 809899 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0275. Min Act: -0.0002

Data Index: 55743 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0269. Min Act: -0.0002

Data Index: 694634 (C4 (Web Text))

Max Activating Token Index: 483