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

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

Neuron 1229 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0796. Min Range: -2.0796

Max Act: 2.0584. Min Act: -0.0000

Data Index: 193905 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 2.0796. Min Range: -2.0796

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1025128 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.9925. Min Act: -0.0000

Data Index: 1040153 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 2.0796. Min Range: -2.0796

Max Act: 2.0796. Min Act: -0.0000

Data Index: 435993 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.9849. Min Act: -0.0000

Data Index: 93255 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6940. Min Act: -0.0000

Data Index: 1269664 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.8691. Min Act: -0.0000

Data Index: 285772 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.7289. Min Act: -0.0000

Data Index: 1041982 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.7042. Min Act: -0.0000

Data Index: 762849 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.7693. Min Act: -0.0000

Data Index: 1082534 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.5955. Min Act: -0.0000

Data Index: 588886 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1118775 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6541. Min Act: -0.0000

Data Index: 230117 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.4853. Min Act: -0.0000

Data Index: 5946 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.4519. Min Act: -0.0000

Data Index: 3644 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.3347. Min Act: -0.0000

Data Index: 376452 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.3082. Min Act: -0.0000

Data Index: 311054 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1246973 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.2624. Min Act: -0.0000

Data Index: 509646 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.2898. Min Act: -0.0000

Data Index: 851391 (C4 (Web Text))

Max Activating Token Index: 536