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

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

Neuron 252 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0380. Min Act: -0.0005

Data Index: 1223619 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0005

Data Index: 907795 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0378. Min Act: -0.0005

Data Index: 1221892 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0363. Min Act: -0.0006

Data Index: 819931 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0357. Min Act: -0.0005

Data Index: 77755 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0353. Min Act: -0.0005

Data Index: 1232502 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1023404 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1269818 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0346. Min Act: -0.0005

Data Index: 1135195 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0351. Min Act: -0.0005

Data Index: 952679 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0344. Min Act: -0.0005

Data Index: 1346620 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1179838 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0347. Min Act: -0.0006

Data Index: 733248 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0335. Min Act: -0.0006

Data Index: 452609 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0333. Min Act: -0.0005

Data Index: 707830 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1320522 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0332. Min Act: -0.0006

Data Index: 320228 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0331. Min Act: -0.0005

Data Index: 234087 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0331. Min Act: -0.0005

Data Index: 214274 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0337. Min Act: -0.0005

Data Index: 398239 (C4 (Web Text))

Max Activating Token Index: 612