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

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

Neuron 4957 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0003

Data Index: 3855 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0431. Min Act: -0.0002

Data Index: 361088 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0382. Min Act: -0.0002

Data Index: 948308 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0392. Min Act: -0.0003

Data Index: 204936 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1140491 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0373. Min Act: -0.0002

Data Index: 341165 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0376. Min Act: -0.0003

Data Index: 422541 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0375. Min Act: -0.0003

Data Index: 196187 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1072974 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0336. Min Act: -0.0003

Data Index: 267621 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1235891 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1108486 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1258111 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0322. Min Act: -0.0003

Data Index: 409606 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0327. Min Act: -0.0003

Data Index: 408177 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0326. Min Act: -0.0003

Data Index: 879003 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0341. Min Act: -0.0002

Data Index: 103029 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1173766 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0315. Min Act: -0.0003

Data Index: 453761 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1132968 (C4 (Web Text))

Max Activating Token Index: 740