Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 631 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1260332 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0965. Min Act: -0.0001

Data Index: 86902 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1151334 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0866. Min Act: -0.0001

Data Index: 626130 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1232466 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0869. Min Act: -0.0001

Data Index: 103989 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0882. Min Act: -0.0001

Data Index: 496409 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0845. Min Act: -0.0001

Data Index: 816998 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0804. Min Act: -0.0001

Data Index: 867084 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0783. Min Act: -0.0001

Data Index: 8105 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1132819 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0757. Min Act: -0.0001

Data Index: 68979 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0765. Min Act: -0.0001

Data Index: 337083 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1290628 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0729. Min Act: -0.0001

Data Index: 753066 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0672. Min Act: -0.0001

Data Index: 443463 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0753. Min Act: -0.0001

Data Index: 931379 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0696. Min Act: -0.0001

Data Index: 180462 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0744. Min Act: -0.0001

Data Index: 678740 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0768. Min Act: -0.0001

Data Index: 66175 (C4 (Web Text))

Max Activating Token Index: 787