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

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

Neuron 3826 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: 1.8739. Min Range: -1.8739

Max Act: 1.8739. Min Act: -0.0000

Data Index: 32703 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.4383. Min Act: -0.0000

Data Index: 757196 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.5013. Min Act: -0.0000

Data Index: 983783 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.2489. Min Act: -0.0000

Data Index: 864312 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.3190. Min Act: -0.0000

Data Index: 151769 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1048935 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.2699. Min Act: -0.0000

Data Index: 593006 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.1177. Min Act: -0.0000

Data Index: 758272 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.1749. Min Act: -0.0000

Data Index: 782491 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.1081. Min Act: -0.0000

Data Index: 20066 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1154515 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.0801. Min Act: -0.0000

Data Index: 688059 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.0653. Min Act: -0.0000

Data Index: 518756 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.8739. Min Range: -1.8739

Max Act: 0.9999. Min Act: -0.0000

Data Index: 166201 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.8739. Min Range: -1.8739

Max Act: 0.9961. Min Act: -0.0000

Data Index: 398784 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.0599. Min Act: -0.0000

Data Index: 286046 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.0573. Min Act: -0.0000

Data Index: 273559 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.8739. Min Range: -1.8739

Max Act: 0.9810. Min Act: -0.0000

Data Index: 534861 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.8739. Min Range: -1.8739

Max Act: 1.0271. Min Act: -0.0000

Data Index: 961784 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.8739. Min Range: -1.8739

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1112072 (C4 (Web Text))

Max Activating Token Index: 874