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

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

Neuron 2158 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1243776 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1031578 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.3335. Min Act: -0.0000

Data Index: 191997 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.3047. Min Act: -0.0000

Data Index: 42695 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2731. Min Act: -0.0000

Data Index: 449855 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2733. Min Act: -0.0000

Data Index: 865926 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2819. Min Act: -0.0000

Data Index: 352514 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2548. Min Act: -0.0000

Data Index: 774515 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2546. Min Act: -0.0000

Data Index: 970387 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2435. Min Act: -0.0000

Data Index: 739643 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2498. Min Act: -0.0000

Data Index: 885651 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1103431 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2503. Min Act: -0.0000

Data Index: 960991 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2484. Min Act: -0.0000

Data Index: 904453 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2353. Min Act: -0.0000

Data Index: 243371 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2498. Min Act: -0.0000

Data Index: 389809 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2371. Min Act: -0.0000

Data Index: 508432 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2292. Min Act: -0.0000

Data Index: 112918 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2285. Min Act: -0.0000

Data Index: 697958 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.3463. Min Range: -0.3463

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1142426 (C4 (Web Text))

Max Activating Token Index: 699