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

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

Neuron 4629 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: 6.8813. Min Range: -6.8813

Max Act: 6.8813. Min Act: -0.0000

Data Index: 796709 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 6.8813. Min Range: -6.8813

Max Act: 5.9053. Min Act: -0.0000

Data Index: 655660 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 6.8813. Min Range: -6.8813

Max Act: 5.1559. Min Act: -0.0000

Data Index: 1071902 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 6.8813. Min Range: -6.8813

Max Act: 5.1171. Min Act: -0.0000

Data Index: 1131164 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.8765. Min Act: -0.0000

Data Index: 1173946 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.8561. Min Act: -0.0000

Data Index: 453577 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.7885. Min Act: -0.0000

Data Index: 679676 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.1178. Min Act: -0.0000

Data Index: 1030811 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.3630. Min Act: -0.0000

Data Index: 1334377 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.4798. Min Act: -0.0000

Data Index: 392168 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.4634. Min Act: -0.0000

Data Index: 371800 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.5700. Min Act: -0.0000

Data Index: 1314186 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.5495. Min Act: -0.0000

Data Index: 646822 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.3711. Min Act: -0.0000

Data Index: 1164732 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.0007. Min Act: -0.0000

Data Index: 700006 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.1126. Min Act: -0.0000

Data Index: 391113 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.3916. Min Act: -0.0000

Data Index: 691750 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.0389. Min Act: -0.0000

Data Index: 577518 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 6.8813. Min Range: -6.8813

Max Act: 4.1771. Min Act: -0.0000

Data Index: 191773 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 6.8813. Min Range: -6.8813

Max Act: 3.9335. Min Act: -0.0000

Data Index: 679120 (C4 (Web Text))

Max Activating Token Index: 872