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

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

Neuron 2241 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1780. Min Act: -0.0002

Data Index: 1348103 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1745. Min Act: -0.0002

Data Index: 930864 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1916. Min Act: -0.0002

Data Index: 371289 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1519. Min Act: -0.0002

Data Index: 962635 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1574. Min Act: -0.0002

Data Index: 165837 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1401. Min Act: -0.0002

Data Index: 84028 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1381. Min Act: -0.0001

Data Index: 750855 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1335. Min Act: -0.0002

Data Index: 628822 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1401. Min Act: -0.0002

Data Index: 1254725 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1430. Min Act: -0.0002

Data Index: 670402 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1237571 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1374. Min Act: -0.0002

Data Index: 924161 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1277. Min Act: -0.0002

Data Index: 137455 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1434. Min Act: -0.0002

Data Index: 394629 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1419. Min Act: -0.0002

Data Index: 857257 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1367. Min Act: -0.0002

Data Index: 129365 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1187378 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1349. Min Act: -0.0001

Data Index: 49742 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1332. Min Act: -0.0002

Data Index: 160207 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1239. Min Act: -0.0001

Data Index: 977762 (C4 (Web Text))

Max Activating Token Index: 575