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

Dataset: The Pile

Neuron 1113 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: 1.6901. Min Range: -1.6901

Max Act: 1.6124. Min Act: -0.0000

Data Index: 700812 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6901. Min Act: -0.0000

Data Index: 309228 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.4573. Min Act: -0.0000

Data Index: 1601382 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.4938. Min Act: -0.0000

Data Index: 1194249 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.4774. Min Act: -0.0000

Data Index: 575834 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.4613. Min Act: -0.0000

Data Index: 254926 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1979820 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.4097. Min Act: -0.0000

Data Index: 1481654 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1944932 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.1837. Min Act: -0.0000

Data Index: 1700352 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.3107. Min Act: -0.0000

Data Index: 901439 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.2403. Min Act: -0.0000

Data Index: 556753 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.2461. Min Act: -0.0000

Data Index: 529059 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.2471. Min Act: -0.0000

Data Index: 1132344 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1442684 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.2815. Min Act: -0.0000

Data Index: 933059 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1665937 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.1129. Min Act: -0.0000

Data Index: 846450 (The Pile)

Max Activating Token Index: 551

Text #18

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1657085 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.1698. Min Act: -0.0000

Data Index: 1172911 (The Pile)

Max Activating Token Index: 148