Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 573 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3966. Min Range: -2.3966

Max Act: 2.3966. Min Act: -0.0000

Data Index: 30963 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 2.3966. Min Range: -2.3966

Max Act: 2.1814. Min Act: -0.0000

Data Index: 23229 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 2.3966. Min Range: -2.3966

Max Act: 2.0545. Min Act: -0.0000

Data Index: 273067 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.9876. Min Act: -0.0000

Data Index: 798647 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 2.3966. Min Range: -2.3966

Max Act: 2.0788. Min Act: -0.0000

Data Index: 316259 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 2.3966. Min Range: -2.3966

Max Act: 2.0745. Min Act: -0.0000

Data Index: 64473 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 2.3966. Min Range: -2.3966

Max Act: 2.0759. Min Act: -0.0000

Data Index: 1031935 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.9430. Min Act: -0.0000

Data Index: 980925 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 2.3966. Min Range: -2.3966

Max Act: 2.0216. Min Act: -0.0000

Data Index: 1092907 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.8862. Min Act: -0.0000

Data Index: 262434 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.8629. Min Act: -0.0000

Data Index: 823135 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.8074. Min Act: -0.0000

Data Index: 541419 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.7864. Min Act: -0.0000

Data Index: 165017 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.7752. Min Act: -0.0000

Data Index: 700282 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.8536. Min Act: -0.0000

Data Index: 482687 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.6446. Min Act: -0.0000

Data Index: 80788 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.7007. Min Act: -0.0000

Data Index: 1338844 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.9055. Min Act: -0.0000

Data Index: 30649 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.6863. Min Act: -0.0000

Data Index: 280993 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 2.3966. Min Range: -2.3966

Max Act: 1.6876. Min Act: -0.0000

Data Index: 137698 (C4 (Web Text))

Max Activating Token Index: 775