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

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

Neuron 1003 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3318. Min Range: -1.3318

Max Act: 1.3318. Min Act: -0.0001

Data Index: 1028087 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.3318. Min Range: -1.3318

Max Act: 1.1652. Min Act: -0.0001

Data Index: 986160 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 1.3318. Min Range: -1.3318

Max Act: 1.0621. Min Act: -0.0001

Data Index: 193285 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.3318. Min Range: -1.3318

Max Act: 1.0650. Min Act: -0.0001

Data Index: 1179250 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 1.3318. Min Range: -1.3318

Max Act: 1.1390. Min Act: -0.0001

Data Index: 673795 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9671. Min Act: -0.0001

Data Index: 1203701 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.3318. Min Range: -1.3318

Max Act: 1.0060. Min Act: -0.0001

Data Index: 296634 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9634. Min Act: -0.0001

Data Index: 459684 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9243. Min Act: -0.0001

Data Index: 910757 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9444. Min Act: -0.0001

Data Index: 457045 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.8530. Min Act: -0.0001

Data Index: 228154 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9925. Min Act: -0.0001

Data Index: 106073 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 1.3318. Min Range: -1.3318

Max Act: 1.0127. Min Act: -0.0001

Data Index: 1963 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9201. Min Act: -0.0001

Data Index: 1138442 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9498. Min Act: -0.0001

Data Index: 1185617 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9668. Min Act: -0.0001

Data Index: 1053737 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9299. Min Act: -0.0001

Data Index: 813616 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.8716. Min Act: -0.0001

Data Index: 780398 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9166. Min Act: -0.0001

Data Index: 1266957 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.3318. Min Range: -1.3318

Max Act: 0.9733. Min Act: -0.0001

Data Index: 1124224 (C4 (Web Text))

Max Activating Token Index: 599