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

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

Neuron 818 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0044. Min Act: -0.0002

Data Index: 858959 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0044. Min Act: -0.0001

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0043. Min Act: -0.0001

Data Index: 1032219 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0043. Min Act: -0.0002

Data Index: 679920 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0042. Min Act: -0.0002

Data Index: 1209719 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0042. Min Act: -0.0001

Data Index: 1057378 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0041. Min Act: -0.0002

Data Index: 791380 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1558897 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1072738 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0040. Min Act: -0.0001

Data Index: 186646 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1058345 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1011692 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 192408 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 316336 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 901113 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 985726 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 219995 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 801199 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1257800 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0039. Min Act: -0.0002

Data Index: 260391 (C4 (Web Text))

Max Activating Token Index: 47