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

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

Neuron 3202 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: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0002

Data Index: 553488 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0468. Min Act: -0.0002

Data Index: 963374 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0426. Min Act: -0.0002

Data Index: 45973 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0411. Min Act: -0.0002

Data Index: 996615 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0404. Min Act: -0.0002

Data Index: 538041 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0431. Min Act: -0.0002

Data Index: 491443 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0414. Min Act: -0.0002

Data Index: 152999 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1040096 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0396. Min Act: -0.0002

Data Index: 574501 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0383. Min Act: -0.0002

Data Index: 274262 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0375. Min Act: -0.0002

Data Index: 505299 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0371. Min Act: -0.0002

Data Index: 536124 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1002177 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0385. Min Act: -0.0002

Data Index: 553210 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1051371 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0383. Min Act: -0.0002

Data Index: 808620 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1271795 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0380. Min Act: -0.0002

Data Index: 304851 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0338. Min Act: -0.0002

Data Index: 826465 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0364. Min Act: -0.0002

Data Index: 730779 (C4 (Web Text))

Max Activating Token Index: 38