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

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

Neuron 5055 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0409. Min Range: -1.0409

Max Act: 1.0409. Min Act: -0.0000

Data Index: 680252 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9091. Min Act: -0.0000

Data Index: 113626 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.0409. Min Range: -1.0409

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1111398 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9269. Min Act: -0.0000

Data Index: 295372 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9309. Min Act: -0.0000

Data Index: 27030 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9669. Min Act: -0.0000

Data Index: 907940 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1249592 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8901. Min Act: -0.0000

Data Index: 415369 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8835. Min Act: -0.0000

Data Index: 99114 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1017185 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8287. Min Act: -0.0000

Data Index: 538564 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9944. Min Act: -0.0000

Data Index: 647432 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8366. Min Act: -0.0000

Data Index: 302136 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7582. Min Act: -0.0000

Data Index: 109642 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1160979 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7853. Min Act: -0.0000

Data Index: 868873 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.5956. Min Act: -0.0000

Data Index: 106785 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1435659 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7726. Min Act: -0.0000

Data Index: 546227 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1354339 (C4 (Web Text))

Max Activating Token Index: 232