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

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

Neuron 2240 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: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1298853 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0384. Min Act: -0.0002

Data Index: 613825 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0353. Min Act: -0.0002

Data Index: 909454 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0331. Min Act: -0.0002

Data Index: 857625 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0333. Min Act: -0.0002

Data Index: 220198 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0334. Min Act: -0.0002

Data Index: 174190 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1269048 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0319. Min Act: -0.0002

Data Index: 453512 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1239577 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1316395 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0312. Min Act: -0.0002

Data Index: 392237 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0299. Min Act: -0.0002

Data Index: 516992 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0302. Min Act: -0.0002

Data Index: 752003 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1132412 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0302. Min Act: -0.0002

Data Index: 278406 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0295. Min Act: -0.0002

Data Index: 504629 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0308. Min Act: -0.0002

Data Index: 569883 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0295. Min Act: -0.0002

Data Index: 234445 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0295. Min Act: -0.0002

Data Index: 694098 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1238676 (C4 (Web Text))

Max Activating Token Index: 735