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

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

Neuron 3612 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.6153. Min Act: -0.0000

Data Index: 478189 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.4310. Min Act: -0.0000

Data Index: 273113 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.4142. Min Act: -0.0000

Data Index: 599243 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.4051. Min Act: -0.0000

Data Index: 401737 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.4083. Min Act: -0.0000

Data Index: 656088 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3978. Min Act: -0.0000

Data Index: 434475 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3755. Min Act: -0.0000

Data Index: 531402 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3278. Min Act: -0.0000

Data Index: 1313595 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3711. Min Act: -0.0000

Data Index: 429666 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3662. Min Act: -0.0000

Data Index: 1458022 (Python Code)

Max Activating Token Index: 84

Text #10

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3176. Min Act: -0.0000

Data Index: 304053 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3544. Min Act: -0.0000

Data Index: 480169 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3158. Min Act: -0.0000

Data Index: 847075 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.2990. Min Act: -0.0000

Data Index: 387048 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3342. Min Act: -0.0000

Data Index: 617116 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.2782. Min Act: -0.0000

Data Index: 918530 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.2759. Min Act: -0.0000

Data Index: 1212813 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3113. Min Act: -0.0000

Data Index: 237802 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.3068. Min Act: -0.0000

Data Index: 979493 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 1.6153. Min Range: -1.6153

Max Act: 1.2392. Min Act: -0.0000

Data Index: 643042 (C4 (Web Text))

Max Activating Token Index: 846