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

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

Neuron 1970 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0006

Data Index: 1305554 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0327. Min Act: -0.0006

Data Index: 315104 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0296. Min Act: -0.0006

Data Index: 169502 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0293. Min Act: -0.0006

Data Index: 83616 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1339667 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0283. Min Act: -0.0005

Data Index: 137481 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0279. Min Act: -0.0006

Data Index: 326655 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0279. Min Act: -0.0006

Data Index: 779446 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0283. Min Act: -0.0005

Data Index: 704491 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0277. Min Act: -0.0006

Data Index: 613347 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0277. Min Act: -0.0006

Data Index: 716808 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0274. Min Act: -0.0006

Data Index: 2052 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0274. Min Act: -0.0006

Data Index: 837790 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0284. Min Act: -0.0006

Data Index: 739778 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0273. Min Act: -0.0006

Data Index: 851954 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0250. Min Act: -0.0005

Data Index: 106162 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0271. Min Act: -0.0006

Data Index: 600308 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0269. Min Act: -0.0006

Data Index: 908666 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0268. Min Act: -0.0006

Data Index: 933823 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0261. Min Act: -0.0006

Data Index: 826302 (C4 (Web Text))

Max Activating Token Index: 854