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

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

Neuron 228 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: 0.0339. Min Range: -0.0339

Max Act: 0.0334. Min Act: -0.0006

Data Index: 770509 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0006

Data Index: 641515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0327. Min Act: -0.0006

Data Index: 443720 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0326. Min Act: -0.0006

Data Index: 1357190 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0310. Min Act: -0.0006

Data Index: 249546 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0313. Min Act: -0.0006

Data Index: 794979 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0303. Min Act: -0.0006

Data Index: 609239 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0302. Min Act: -0.0006

Data Index: 263940 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0307. Min Act: -0.0006

Data Index: 900505 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1170419 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1034137 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0309. Min Act: -0.0006

Data Index: 427856 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0295. Min Act: -0.0006

Data Index: 875669 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0287. Min Act: -0.0006

Data Index: 385808 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0306. Min Act: -0.0006

Data Index: 1288011 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0286. Min Act: -0.0006

Data Index: 652498 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1211949 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0293. Min Act: -0.0006

Data Index: 625603 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0292. Min Act: -0.0006

Data Index: 588985 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0298. Min Act: -0.0006

Data Index: 245389 (C4 (Web Text))

Max Activating Token Index: 269