Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1422 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0004

Data Index: 999576 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0403. Min Act: -0.0005

Data Index: 1089378 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0404. Min Act: -0.0004

Data Index: 110525 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0402. Min Act: -0.0005

Data Index: 1148718 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0385. Min Act: -0.0005

Data Index: 792077 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0386. Min Act: -0.0005

Data Index: 122468 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0384. Min Act: -0.0005

Data Index: 645583 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0379. Min Act: -0.0004

Data Index: 32163 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0378. Min Act: -0.0004

Data Index: 1006208 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0367. Min Act: -0.0004

Data Index: 128723 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0369. Min Act: -0.0005

Data Index: 435671 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0358. Min Act: -0.0004

Data Index: 572053 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0357. Min Act: -0.0004

Data Index: 475166 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0355. Min Act: -0.0004

Data Index: 1488076 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0356. Min Act: -0.0004

Data Index: 1404197 (Python Code)

Max Activating Token Index: 557

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0345. Min Act: -0.0004

Data Index: 984669 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0352. Min Act: -0.0004

Data Index: 80844 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0352. Min Act: -0.0004

Data Index: 1072795 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0351. Min Act: -0.0005

Data Index: 1050898 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1042193 (C4 (Web Text))

Max Activating Token Index: 1010