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

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

Neuron 1799 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: 0.9009. Min Range: -0.9009

Max Act: 0.8513. Min Act: -0.0000

Data Index: 649230 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.9009. Min Act: -0.0000

Data Index: 888591 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1433166 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8833. Min Act: -0.0000

Data Index: 726392 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8444. Min Act: -0.0000

Data Index: 989936 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1068353 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8544. Min Act: -0.0001

Data Index: 1567073 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8173. Min Act: -0.0001

Data Index: 979970 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7358. Min Act: -0.0000

Data Index: 805762 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7524. Min Act: -0.0000

Data Index: 414158 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7991. Min Act: -0.0001

Data Index: 1646439 (Python Code)

Max Activating Token Index: 245

Text #11

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7520. Min Act: -0.0000

Data Index: 638992 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1127026 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7431. Min Act: -0.0000

Data Index: 574275 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7412. Min Act: -0.0001

Data Index: 1485355 (Python Code)

Max Activating Token Index: 115

Text #15

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7635. Min Act: -0.0001

Data Index: 1470803 (Python Code)

Max Activating Token Index: 422

Text #16

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8288. Min Act: -0.0000

Data Index: 658278 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7798. Min Act: -0.0000

Data Index: 375753 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7564. Min Act: -0.0000

Data Index: 493298 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8055. Min Act: -0.0000

Data Index: 361492 (C4 (Web Text))

Max Activating Token Index: 943