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

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

Neuron 4329 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0509. Min Act: -0.0002

Data Index: 810850 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1319887 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1002109 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1349316 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0434. Min Act: -0.0003

Data Index: 892668 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0429. Min Act: -0.0003

Data Index: 930844 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1651048 (Python Code)

Max Activating Token Index: 797

Text #7

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0443. Min Act: -0.0002

Data Index: 970651 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0426. Min Act: -0.0002

Data Index: 262621 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0429. Min Act: -0.0003

Data Index: 890316 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0416. Min Act: -0.0003

Data Index: 532600 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0429. Min Act: -0.0002

Data Index: 74353 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1286105 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0415. Min Act: -0.0002

Data Index: 206178 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0406. Min Act: -0.0003

Data Index: 314515 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0384. Min Act: -0.0003

Data Index: 443904 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0380. Min Act: -0.0003

Data Index: 675798 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0391. Min Act: -0.0003

Data Index: 773951 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1128110 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1462399 (Python Code)

Max Activating Token Index: 410