Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 70 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.4247. Min Act: -0.0000

Data Index: 805633 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.4254. Min Act: -0.0001

Data Index: 627754 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.4005. Min Act: -0.0001

Data Index: 1228744 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.4106. Min Act: -0.0000

Data Index: 168782 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3765. Min Act: -0.0000

Data Index: 526267 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3733. Min Act: -0.0000

Data Index: 14378 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3614. Min Act: -0.0000

Data Index: 789430 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3661. Min Act: -0.0001

Data Index: 380841 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3660. Min Act: -0.0000

Data Index: 947074 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3661. Min Act: -0.0000

Data Index: 213599 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1166782 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3563. Min Act: -0.0001

Data Index: 149405 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3380. Min Act: -0.0001

Data Index: 301357 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3390. Min Act: -0.0001

Data Index: 218652 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1341017 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3603. Min Act: -0.0001

Data Index: 800454 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1177091 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3465. Min Act: -0.0000

Data Index: 372504 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3558. Min Act: -0.0001

Data Index: 99675 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3399. Min Act: -0.0000

Data Index: 86373 (C4 (Web Text))

Max Activating Token Index: 57