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

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

Neuron 682 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: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1315795 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0465. Min Act: -0.0002

Data Index: 421131 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1003311 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0435. Min Act: -0.0002

Data Index: 973448 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1276157 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0432. Min Act: -0.0002

Data Index: 578396 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0388. Min Act: -0.0002

Data Index: 209132 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0378. Min Act: -0.0002

Data Index: 277485 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0391. Min Act: -0.0002

Data Index: 686180 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0376. Min Act: -0.0002

Data Index: 194189 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0399. Min Act: -0.0002

Data Index: 213976 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0378. Min Act: -0.0002

Data Index: 540996 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1099930 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0412. Min Act: -0.0002

Data Index: 783108 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0394. Min Act: -0.0002

Data Index: 974008 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0373. Min Act: -0.0002

Data Index: 787945 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0369. Min Act: -0.0002

Data Index: 70810 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1261295 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1354092 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0365. Min Act: -0.0002

Data Index: 871488 (C4 (Web Text))

Max Activating Token Index: 380