Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5092 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0001

Data Index: 324021 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0376. Min Act: -0.0001

Data Index: 112624 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1240357 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0372. Min Act: -0.0001

Data Index: 925877 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1163901 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0351. Min Act: -0.0001

Data Index: 657829 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1083241 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1292073 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1323086 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0327. Min Act: -0.0001

Data Index: 45417 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0274. Min Act: -0.0001

Data Index: 941801 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0312. Min Act: -0.0001

Data Index: 665508 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0308. Min Act: -0.0001

Data Index: 702775 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0308. Min Act: -0.0001

Data Index: 381263 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1585904 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0235. Min Act: -0.0001

Data Index: 166436 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1150236 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0272. Min Act: -0.0001

Data Index: 591023 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0268. Min Act: -0.0001

Data Index: 390016 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1282536 (C4 (Web Text))

Max Activating Token Index: 472