Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2657 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0446. Min Act: -0.0000

Data Index: 656403 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0432. Min Act: -0.0000

Data Index: 814171 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0454. Min Act: -0.0000

Data Index: 48069 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0401. Min Act: -0.0000

Data Index: 26529 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0396. Min Act: -0.0000

Data Index: 310292 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1334445 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0397. Min Act: -0.0000

Data Index: 463075 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0359. Min Act: -0.0000

Data Index: 850256 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0344. Min Act: -0.0000

Data Index: 893832 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1210132 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0366. Min Act: -0.0000

Data Index: 120505 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0363. Min Act: -0.0000

Data Index: 445148 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0358. Min Act: -0.0000

Data Index: 339046 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0372. Min Act: -0.0000

Data Index: 995494 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1283043 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0350. Min Act: -0.0000

Data Index: 963132 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0350. Min Act: -0.0000

Data Index: 106835 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1444988 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1149558 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1356583 (C4 (Web Text))

Max Activating Token Index: 923