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

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

Neuron 3306 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6447. Min Act: -0.0002

Data Index: 746352 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6396. Min Act: -0.0002

Data Index: 716624 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6325. Min Act: -0.0002

Data Index: 1307501 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6443. Min Act: -0.0002

Data Index: 1106994 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6231. Min Act: -0.0002

Data Index: 798617 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6120. Min Act: -0.0002

Data Index: 1014528 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5935. Min Act: -0.0002

Data Index: 1302134 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6272. Min Act: -0.0002

Data Index: 1326875 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6353. Min Act: -0.0002

Data Index: 821280 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5774. Min Act: -0.0002

Data Index: 475688 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5912. Min Act: -0.0002

Data Index: 1049445 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5841. Min Act: -0.0002

Data Index: 187995 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6187. Min Act: -0.0002

Data Index: 1166274 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5923. Min Act: -0.0002

Data Index: 1226329 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5275. Min Act: -0.0002

Data Index: 357325 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5925. Min Act: -0.0002

Data Index: 60956 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5551. Min Act: -0.0002

Data Index: 867959 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5524. Min Act: -0.0002

Data Index: 1981 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5514. Min Act: -0.0002

Data Index: 104119 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5873. Min Act: -0.0002

Data Index: 125589 (C4 (Web Text))

Max Activating Token Index: 50