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

Dataset: The Pile

Neuron 4116 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: 0.4665. Min Range: -0.4665

Max Act: 0.4572. Min Act: -0.0000

Data Index: 807132 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4665. Min Act: -0.0000

Data Index: 560468 (The Pile)

Max Activating Token Index: 332

Text #2

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1407336 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4432. Min Act: -0.0000

Data Index: 442183 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1907279 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4208. Min Act: 0.0000

Data Index: 1391973 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4046. Min Act: -0.0000

Data Index: 804143 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1390420 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4070. Min Act: 0.0000

Data Index: 1944906 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4043. Min Act: -0.0000

Data Index: 269133 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1739426 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1462229 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4000. Min Act: 0.0000

Data Index: 1273278 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3811. Min Act: -0.0000

Data Index: 185055 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3803. Min Act: -0.0000

Data Index: 895189 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3997. Min Act: -0.0000

Data Index: 257590 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3820. Min Act: 0.0000

Data Index: 750357 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3805. Min Act: -0.0000

Data Index: 752619 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1097921 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1255208 (The Pile)

Max Activating Token Index: 370