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

Dataset: The Pile

Neuron 1736 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: 1.7994. Min Range: -1.7994

Max Act: 1.7994. Min Act: -0.0000

Data Index: 644543 (The Pile)

Max Activating Token Index: 260

Text #1

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7816. Min Act: -0.0000

Data Index: 293888 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.4452. Min Act: -0.0000

Data Index: 797003 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.4805. Min Act: -0.0000

Data Index: 132242 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.5493. Min Act: -0.0000

Data Index: 406072 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.4068. Min Act: -0.0000

Data Index: 930555 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.3278. Min Act: -0.0000

Data Index: 723827 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.2793. Min Act: -0.0000

Data Index: 993241 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1920026 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.0698. Min Act: -0.0000

Data Index: 941644 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1078856 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.2363. Min Act: -0.0000

Data Index: 67678 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1920529 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 1.7994. Min Range: -1.7994

Max Act: 0.9816. Min Act: -0.0000

Data Index: 808913 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.0892. Min Act: -0.0000

Data Index: 964975 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 1.7994. Min Range: -1.7994

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1626087 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.1188. Min Act: -0.0000

Data Index: 653956 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1592737 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1642306 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 1.7994. Min Range: -1.7994

Max Act: 0.9772. Min Act: -0.0000

Data Index: 85045 (The Pile)

Max Activating Token Index: 649