Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 705 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1345211 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0393. Min Act: -0.0002

Data Index: 438263 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1014252 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1029963 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1231718 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0367. Min Act: -0.0002

Data Index: 632506 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1175794 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0378. Min Act: -0.0002

Data Index: 344143 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1120669 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1348579 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1551552 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1033424 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0357. Min Act: -0.0002

Data Index: 372891 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0352. Min Act: -0.0002

Data Index: 616161 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0357. Min Act: -0.0002

Data Index: 441903 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0362. Min Act: -0.0002

Data Index: 659672 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0353. Min Act: -0.0002

Data Index: 571831 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0352. Min Act: -0.0002

Data Index: 870404 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0354. Min Act: -0.0002

Data Index: 933826 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1197558 (C4 (Web Text))

Max Activating Token Index: 724