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

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

Neuron 4621 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: 2.9949. Min Range: -2.9949

Max Act: 2.9949. Min Act: -0.0000

Data Index: 906582 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.7512. Min Act: -0.0000

Data Index: 263775 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.3096. Min Act: -0.0000

Data Index: 921771 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.3660. Min Act: -0.0000

Data Index: 973716 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.3559. Min Act: -0.0000

Data Index: 627575 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.4664. Min Act: -0.0000

Data Index: 654187 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.0666. Min Act: -0.0000

Data Index: 378616 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.1652. Min Act: -0.0000

Data Index: 1069064 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.2738. Min Act: -0.0000

Data Index: 715076 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.2642. Min Act: -0.0000

Data Index: 978773 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.1451. Min Act: -0.0000

Data Index: 92 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.1290. Min Act: -0.0000

Data Index: 152316 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.2184. Min Act: -0.0000

Data Index: 130429 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 2.9949. Min Range: -2.9949

Max Act: 1.9804. Min Act: -0.0000

Data Index: 1005218 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 2.9949. Min Range: -2.9949

Max Act: 1.9683. Min Act: -0.0000

Data Index: 615228 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.0483. Min Act: -0.0000

Data Index: 576293 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 2.9949. Min Range: -2.9949

Max Act: 2.0222. Min Act: -0.0000

Data Index: 923052 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 2.9949. Min Range: -2.9949

Max Act: 1.9124. Min Act: -0.0000

Data Index: 568294 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 2.9949. Min Range: -2.9949

Max Act: 1.9052. Min Act: -0.0000

Data Index: 9630 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 2.9949. Min Range: -2.9949

Max Act: 1.9660. Min Act: -0.0000

Data Index: 33255 (C4 (Web Text))

Max Activating Token Index: 979