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

Dataset: The Pile

Neuron 2105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2646. Min Act: -0.0000

Data Index: 1468023 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.9358. Min Act: -0.0000

Data Index: 1980017 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2781. Min Act: -0.0000

Data Index: 424120 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2728. Min Act: -0.0000

Data Index: 1117338 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.7731. Min Act: -0.0000

Data Index: 1514782 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1920. Min Act: -0.0000

Data Index: 428476 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1926. Min Act: -0.0000

Data Index: 1008814 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.9621. Min Act: -0.0000

Data Index: 1239372 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.9635. Min Act: -0.0000

Data Index: 869443 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.0807. Min Act: -0.0000

Data Index: 803347 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.3069. Min Act: -0.0000

Data Index: 1602669 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.9001. Min Act: -0.0000

Data Index: 1101483 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.9311. Min Act: -0.0000

Data Index: 671206 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.0613. Min Act: -0.0000

Data Index: 55519 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.0514. Min Act: -0.0000

Data Index: 3318 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.0452. Min Act: -0.0000

Data Index: 999872 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.7478. Min Act: -0.0000

Data Index: 579348 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.9372. Min Act: -0.0000

Data Index: 217033 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.8284. Min Act: -0.0000

Data Index: 1256262 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 3.3069. Min Range: -3.3069

Max Act: 2.8235. Min Act: -0.0000

Data Index: 1435749 (The Pile)

Max Activating Token Index: 195