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

Dataset: The Pile

Neuron 1648 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9539. Min Range: -4.9539

Max Act: 4.9539. Min Act: -0.0000

Data Index: 59745 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 4.9539. Min Range: -4.9539

Max Act: 3.8559. Min Act: -0.0000

Data Index: 1753397 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 4.9539. Min Range: -4.9539

Max Act: 3.1985. Min Act: -0.0000

Data Index: 435850 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 4.9539. Min Range: -4.9539

Max Act: 3.1197. Min Act: -0.0000

Data Index: 1748331 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 4.9539. Min Range: -4.9539

Max Act: 2.5366. Min Act: -0.0000

Data Index: 1895149 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 4.9539. Min Range: -4.9539

Max Act: 2.3903. Min Act: -0.0000

Data Index: 1893854 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.8922. Min Act: -0.0000

Data Index: 1762050 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.6733. Min Act: -0.0000

Data Index: 760659 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.7588. Min Act: -0.0000

Data Index: 489329 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.7540. Min Act: -0.0000

Data Index: 1427080 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.7826. Min Act: -0.0000

Data Index: 1620911 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1149871 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.5309. Min Act: -0.0000

Data Index: 494026 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1408919 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1825729 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.1573. Min Act: -0.0000

Data Index: 558761 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.4333. Min Act: -0.0000

Data Index: 321830 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.3823. Min Act: -0.0000

Data Index: 1399235 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1787028 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 4.9539. Min Range: -4.9539

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1184624 (The Pile)

Max Activating Token Index: 31