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

Dataset: The Pile

Neuron 929 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4995. Min Range: -5.4995

Max Act: 5.4995. Min Act: -0.0000

Data Index: 489306 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 5.4995. Min Range: -5.4995

Max Act: 3.9251. Min Act: -0.0000

Data Index: 977903 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 5.4995. Min Range: -5.4995

Max Act: 3.8431. Min Act: -0.0000

Data Index: 789553 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 5.4995. Min Range: -5.4995

Max Act: 3.6072. Min Act: 0.0000

Data Index: 1289528 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 5.4995. Min Range: -5.4995

Max Act: 3.0269. Min Act: -0.0000

Data Index: 1102775 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 5.4995. Min Range: -5.4995

Max Act: 3.2159. Min Act: -0.0000

Data Index: 1412323 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.9515. Min Act: -0.0000

Data Index: 153133 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.7751. Min Act: -0.0000

Data Index: 1560877 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.7800. Min Act: -0.0000

Data Index: 1180437 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.7433. Min Act: 0.0000

Data Index: 1461072 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.4604. Min Act: -0.0000

Data Index: 399751 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.4709. Min Act: 0.0000

Data Index: 1017517 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.4840. Min Act: -0.0000

Data Index: 3093 (The Pile)

Max Activating Token Index: 391

Text #13

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.1685. Min Act: -0.0000

Data Index: 963127 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.1643. Min Act: -0.0000

Data Index: 51440 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.3523. Min Act: 0.0000

Data Index: 1142509 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.3511. Min Act: -0.0000

Data Index: 506246 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.2363. Min Act: -0.0000

Data Index: 1025179 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.4461. Min Act: -0.0000

Data Index: 32368 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 5.4995. Min Range: -5.4995

Max Act: 2.2915. Min Act: -0.0000

Data Index: 1527727 (The Pile)

Max Activating Token Index: 697