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

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

Neuron 2912 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0002

Data Index: 451817 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0337. Min Act: -0.0002

Data Index: 493969 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0352. Min Act: -0.0002

Data Index: 811351 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0364. Min Act: -0.0002

Data Index: 889831 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1106875 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0359. Min Act: -0.0002

Data Index: 330346 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0367. Min Act: -0.0002

Data Index: 459191 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0332. Min Act: -0.0002

Data Index: 358894 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0376. Min Act: -0.0002

Data Index: 248464 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0343. Min Act: -0.0002

Data Index: 790632 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0352. Min Act: -0.0002

Data Index: 542499 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0341. Min Act: -0.0002

Data Index: 875656 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0341. Min Act: -0.0002

Data Index: 208004 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1241745 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0334. Min Act: -0.0002

Data Index: 523753 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0348. Min Act: -0.0002

Data Index: 869768 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0339. Min Act: -0.0002

Data Index: 386298 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0341. Min Act: -0.0002

Data Index: 965950 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1221755 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0310. Min Act: -0.0002

Data Index: 35534 (C4 (Web Text))

Max Activating Token Index: 540