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

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

Neuron 3048 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: 6.4171. Min Range: -6.4171

Max Act: 6.4171. Min Act: -0.0000

Data Index: 479419 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 6.4171. Min Range: -6.4171

Max Act: 6.2395. Min Act: -0.0000

Data Index: 1305082 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 6.4171. Min Range: -6.4171

Max Act: 6.1061. Min Act: -0.0000

Data Index: 1054020 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 6.4171. Min Range: -6.4171

Max Act: 6.1652. Min Act: -0.0000

Data Index: 914731 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 6.4171. Min Range: -6.4171

Max Act: 6.3505. Min Act: -0.0000

Data Index: 202370 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.8363. Min Act: -0.0000

Data Index: 184664 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 6.4171. Min Range: -6.4171

Max Act: 6.0172. Min Act: -0.0000

Data Index: 993526 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.6022. Min Act: -0.0000

Data Index: 14117 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.5982. Min Act: -0.0000

Data Index: 376886 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.9519. Min Act: -0.0000

Data Index: 1051721 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.9083. Min Act: -0.0000

Data Index: 168990 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 6.4171. Min Range: -6.4171

Max Act: 6.0572. Min Act: -0.0000

Data Index: 798600 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.9910. Min Act: -0.0000

Data Index: 937759 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.5952. Min Act: -0.0000

Data Index: 437120 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.8076. Min Act: -0.0000

Data Index: 1072918 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.9568. Min Act: -0.0000

Data Index: 436993 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.5898. Min Act: -0.0000

Data Index: 598994 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.7487. Min Act: -0.0000

Data Index: 1209956 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.5172. Min Act: -0.0000

Data Index: 100293 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 6.4171. Min Range: -6.4171

Max Act: 5.6016. Min Act: -0.0000

Data Index: 726213 (C4 (Web Text))

Max Activating Token Index: 860