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

Dataset: The Pile

Neuron 1309 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: 1.2901. Min Range: -1.2901

Max Act: 1.2901. Min Act: -0.0000

Data Index: 272594 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1914921 (The Pile)

Max Activating Token Index: 694

Text #2

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9081. Min Act: -0.0000

Data Index: 661925 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1656941 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1435589 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7734. Min Act: -0.0000

Data Index: 926174 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1887456 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1803132 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7587. Min Act: -0.0000

Data Index: 763246 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1059857 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1008240 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1318875 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1311458 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.7767. Min Act: -0.0000

Data Index: 651421 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.6647. Min Act: -0.0000

Data Index: 361043 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1888923 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.6900. Min Act: -0.0000

Data Index: 861841 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.6562. Min Act: -0.0000

Data Index: 282143 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.6407. Min Act: -0.0000

Data Index: 155772 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1595808 (The Pile)

Max Activating Token Index: 654