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

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

Neuron 1581 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7035. Min Range: -2.7035

Max Act: 2.7035. Min Act: -0.0000

Data Index: 190146 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 2.7035. Min Range: -2.7035

Max Act: 2.0870. Min Act: -0.0000

Data Index: 931717 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.9148. Min Act: -0.0000

Data Index: 1012494 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.9416. Min Act: 0.0000

Data Index: 1231409 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.8553. Min Act: 0.0000

Data Index: 1240631 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.8342. Min Act: -0.0000

Data Index: 258249 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.7807. Min Act: -0.0000

Data Index: 210097 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.7780. Min Act: 0.0000

Data Index: 702801 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.6829. Min Act: -0.0000

Data Index: 839560 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.6893. Min Act: -0.0000

Data Index: 579166 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.6114. Min Act: -0.0000

Data Index: 370597 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.6060. Min Act: -0.0000

Data Index: 609980 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.5511. Min Act: -0.0000

Data Index: 1126618 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.5379. Min Act: -0.0000

Data Index: 789102 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.5178. Min Act: -0.0000

Data Index: 786333 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.4005. Min Act: 0.0000

Data Index: 805163 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1190333 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.4744. Min Act: -0.0000

Data Index: 677008 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.4620. Min Act: -0.0000

Data Index: 897364 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 2.7035. Min Range: -2.7035

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1327497 (C4 (Web Text))

Max Activating Token Index: 41