Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5801 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6970. Min Act: -0.0000

Data Index: 1018622 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6194. Min Act: -0.0000

Data Index: 592850 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6149. Min Act: -0.0000

Data Index: 1028287 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.5319. Min Act: -0.0000

Data Index: 856729 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.5648. Min Act: -0.0000

Data Index: 1210088 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6447. Min Act: -0.0000

Data Index: 994814 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1129047 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.4477. Min Act: -0.0000

Data Index: 140509 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.3732. Min Act: -0.0000

Data Index: 228989 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.4016. Min Act: -0.0000

Data Index: 82078 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.3008. Min Act: -0.0000

Data Index: 333356 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.3284. Min Act: -0.0000

Data Index: 874924 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.3219. Min Act: -0.0000

Data Index: 180127 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1342356 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1063915 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.2952. Min Act: -0.0000

Data Index: 490371 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.2058. Min Act: -0.0000

Data Index: 885472 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1503157 (Python Code)

Max Activating Token Index: 952

Text #18

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.2812. Min Act: -0.0000

Data Index: 507050 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1029668 (C4 (Web Text))

Max Activating Token Index: 437