Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 35 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0454. Min Act: -0.0003

Data Index: 575843 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1643865 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0423. Min Act: -0.0003

Data Index: 938839 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1010976 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1018817 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1249462 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1146538 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0380. Min Act: -0.0003

Data Index: 181 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0352. Min Act: -0.0003

Data Index: 124306 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1228705 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0377. Min Act: -0.0003

Data Index: 666331 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0378. Min Act: -0.0003

Data Index: 375328 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1023705 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1593376 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1375025 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0363. Min Act: -0.0003

Data Index: 973904 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0345. Min Act: -0.0003

Data Index: 329491 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1309203 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0352. Min Act: -0.0003

Data Index: 703841 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0361. Min Act: -0.0003

Data Index: 425524 (C4 (Web Text))

Max Activating Token Index: 32