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

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

Neuron 906 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: 2.6865. Min Range: -2.6865

Max Act: 2.6865. Min Act: -0.0000

Data Index: 206667 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 2.6865. Min Range: -2.6865

Max Act: 2.4047. Min Act: -0.0000

Data Index: 256229 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 2.6865. Min Range: -2.6865

Max Act: 2.1220. Min Act: -0.0000

Data Index: 85234 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 2.6865. Min Range: -2.6865

Max Act: 2.1607. Min Act: -0.0000

Data Index: 861451 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 2.6865. Min Range: -2.6865

Max Act: 2.0208. Min Act: -0.0000

Data Index: 1405075 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.8733. Min Act: -0.0000

Data Index: 969939 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.9599. Min Act: -0.0000

Data Index: 696239 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 2.6865. Min Range: -2.6865

Max Act: 2.0245. Min Act: -0.0000

Data Index: 1231108 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.9136. Min Act: -0.0000

Data Index: 373488 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.9085. Min Act: -0.0000

Data Index: 1176468 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.9807. Min Act: -0.0000

Data Index: 655136 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.7279. Min Act: -0.0000

Data Index: 562535 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.8298. Min Act: -0.0000

Data Index: 923798 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.7804. Min Act: -0.0000

Data Index: 874941 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.6839. Min Act: -0.0000

Data Index: 719694 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.8766. Min Act: -0.0000

Data Index: 250364 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.7267. Min Act: -0.0000

Data Index: 210747 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.7390. Min Act: -0.0000

Data Index: 1156914 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.7430. Min Act: -0.0000

Data Index: 85523 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 2.6865. Min Range: -2.6865

Max Act: 1.7270. Min Act: -0.0000

Data Index: 840714 (C4 (Web Text))

Max Activating Token Index: 450