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

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

Neuron 524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0370. Min Act: -0.0000

Data Index: 593068 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0418. Min Act: -0.0000

Data Index: 659146 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0459. Min Act: -0.0000

Data Index: 138120 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0384. Min Act: -0.0000

Data Index: 1423106 (Python Code)

Max Activating Token Index: 705

Text #4

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1096803 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0337. Min Act: -0.0000

Data Index: 872752 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1170046 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1322684 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0333. Min Act: -0.0000

Data Index: 523110 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0333. Min Act: -0.0000

Data Index: 265886 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1495356 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0347. Min Act: -0.0000

Data Index: 495246 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1176598 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1399244 (Python Code)

Max Activating Token Index: 565

Text #14

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0327. Min Act: -0.0000

Data Index: 230674 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1140948 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0291. Min Act: -0.0000

Data Index: 1081665 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1045373 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0295. Min Act: -0.0000

Data Index: 422734 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1365407 (Python Code)

Max Activating Token Index: 558