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

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

Neuron 307 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.1910. Min Act: -0.0000

Data Index: 43871 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.0928. Min Act: -0.0000

Data Index: 908677 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.0802. Min Act: -0.0000

Data Index: 895159 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.0952. Min Act: -0.0000

Data Index: 616863 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1424120 (Python Code)

Max Activating Token Index: 1012

Text #5

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.0077. Min Act: -0.0000

Data Index: 920188 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9063. Min Act: -0.0000

Data Index: 959363 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1473560 (Python Code)

Max Activating Token Index: 513

Text #8

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1334709 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9352. Min Act: -0.0000

Data Index: 170180 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9764. Min Act: -0.0000

Data Index: 355885 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1621510 (Python Code)

Max Activating Token Index: 985

Text #12

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9288. Min Act: -0.0000

Data Index: 78540 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9301. Min Act: -0.0000

Data Index: 445622 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9276. Min Act: -0.0000

Data Index: 266884 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9573. Min Act: -0.0000

Data Index: 604775 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1145281 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9192. Min Act: -0.0000

Data Index: 616370 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9079. Min Act: -0.0000

Data Index: 428756 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9395. Min Act: -0.0000

Data Index: 278160 (C4 (Web Text))

Max Activating Token Index: 669