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

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

Neuron 1009 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0003

Data Index: 1542352 (Python Code)

Max Activating Token Index: 603

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0389. Min Act: -0.0002

Data Index: 390349 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1239081 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0402. Min Act: -0.0003

Data Index: 559531 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0393. Min Act: -0.0003

Data Index: 16029 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0386. Min Act: -0.0003

Data Index: 973339 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0383. Min Act: -0.0003

Data Index: 153638 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1311702 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0374. Min Act: -0.0003

Data Index: 548284 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0384. Min Act: -0.0003

Data Index: 973031 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0372. Min Act: -0.0003

Data Index: 841321 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1205278 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1281435 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0379. Min Act: -0.0003

Data Index: 903387 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1278523 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0361. Min Act: -0.0003

Data Index: 18777 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1109225 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0371. Min Act: -0.0003

Data Index: 930497 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0356. Min Act: -0.0003

Data Index: 296892 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1134733 (C4 (Web Text))

Max Activating Token Index: 961