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

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

Neuron 4715 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0000

Data Index: 574209 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0397. Min Act: -0.0000

Data Index: 762498 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0381. Min Act: -0.0000

Data Index: 551477 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1091694 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1267625 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1519655 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0348. Min Act: -0.0000

Data Index: 599486 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0356. Min Act: -0.0000

Data Index: 643344 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0362. Min Act: -0.0000

Data Index: 997651 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0354. Min Act: -0.0000

Data Index: 562843 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0329. Min Act: -0.0000

Data Index: 235309 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0334. Min Act: -0.0000

Data Index: 358063 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0323. Min Act: -0.0000

Data Index: 999146 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1528843 (Python Code)

Max Activating Token Index: 761

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0311. Min Act: -0.0000

Data Index: 261263 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0331. Min Act: -0.0000

Data Index: 855014 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0329. Min Act: 0.0000

Data Index: 1039156 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0321. Min Act: -0.0000

Data Index: 70421 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1346029 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0321. Min Act: -0.0000

Data Index: 395184 (C4 (Web Text))

Max Activating Token Index: 63