Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1534 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0444. Min Act: -0.0003

Data Index: 820713 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0003

Data Index: 464226 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0438. Min Act: -0.0003

Data Index: 760873 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1033630 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0425. Min Act: -0.0003

Data Index: 955367 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0404. Min Act: -0.0003

Data Index: 199212 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1117944 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1019506 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0370. Min Act: -0.0003

Data Index: 576417 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0375. Min Act: -0.0003

Data Index: 310168 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0404. Min Act: -0.0003

Data Index: 904103 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0392. Min Act: -0.0003

Data Index: 332178 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1165333 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1189942 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0366. Min Act: -0.0003

Data Index: 803958 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0383. Min Act: -0.0003

Data Index: 171768 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0409. Min Act: -0.0003

Data Index: 448956 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1337439 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0396. Min Act: -0.0003

Data Index: 832560 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0380. Min Act: -0.0003

Data Index: 289176 (C4 (Web Text))

Max Activating Token Index: 352