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

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

Neuron 1057 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0293. Min Act: -0.0006

Data Index: 289614 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1072153 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1200472 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0283. Min Act: -0.0006

Data Index: 772060 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0279. Min Act: -0.0006

Data Index: 810965 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0272. Min Act: -0.0006

Data Index: 601114 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0275. Min Act: -0.0006

Data Index: 350082 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0276. Min Act: -0.0006

Data Index: 320292 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0268. Min Act: -0.0006

Data Index: 90679 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0274. Min Act: -0.0006

Data Index: 517410 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0273. Min Act: -0.0006

Data Index: 253049 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0272. Min Act: -0.0006

Data Index: 936074 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0271. Min Act: -0.0006

Data Index: 313239 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0269. Min Act: -0.0006

Data Index: 470775 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0275. Min Act: -0.0006

Data Index: 498137 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0270. Min Act: -0.0006

Data Index: 13550 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0269. Min Act: -0.0006

Data Index: 53109 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0268. Min Act: -0.0006

Data Index: 787086 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1011140 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0268. Min Act: -0.0006

Data Index: 702441 (C4 (Web Text))

Max Activating Token Index: 975