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

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

Neuron 1644 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: 1.1273. Min Range: -1.1273

Max Act: 1.0965. Min Act: -0.0002

Data Index: 576845 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.1273. Min Act: -0.0001

Data Index: 685451 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.1169. Min Act: -0.0002

Data Index: 79293 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.1271. Min Act: -0.0002

Data Index: 1109176 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.1239. Min Act: -0.0001

Data Index: 158520 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0897. Min Act: -0.0002

Data Index: 696110 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0811. Min Act: -0.0002

Data Index: 350269 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.1102. Min Act: -0.0002

Data Index: 800716 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0645. Min Act: -0.0002

Data Index: 605831 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0037. Min Act: -0.0001

Data Index: 611715 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0158. Min Act: -0.0002

Data Index: 148901 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0139. Min Act: -0.0001

Data Index: 584123 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0084. Min Act: -0.0002

Data Index: 268837 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9184. Min Act: -0.0002

Data Index: 213112 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9735. Min Act: -0.0002

Data Index: 868825 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9969. Min Act: -0.0002

Data Index: 1036844 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9911. Min Act: -0.0001

Data Index: 1017630 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9939. Min Act: -0.0001

Data Index: 1162188 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9800. Min Act: -0.0002

Data Index: 1071560 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9752. Min Act: -0.0001

Data Index: 1169797 (C4 (Web Text))

Max Activating Token Index: 54