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

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

Neuron 1549 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: 0.0470. Min Range: -0.0470

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1080119 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1236339 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0417. Min Act: -0.0003

Data Index: 11459 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0401. Min Act: -0.0003

Data Index: 906100 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0407. Min Act: -0.0003

Data Index: 754787 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1147493 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0375. Min Act: -0.0003

Data Index: 365872 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0368. Min Act: -0.0003

Data Index: 777423 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1080527 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0360. Min Act: -0.0003

Data Index: 958607 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0359. Min Act: -0.0003

Data Index: 787762 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1304014 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0353. Min Act: -0.0003

Data Index: 763371 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0360. Min Act: -0.0003

Data Index: 850708 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1273995 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0350. Min Act: -0.0003

Data Index: 324964 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1071190 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1001197 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0352. Min Act: -0.0003

Data Index: 239998 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0343. Min Act: -0.0003

Data Index: 770331 (C4 (Web Text))

Max Activating Token Index: 151