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

Dataset: The Pile

Neuron 4369 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.5383. Min Act: -0.0000

Data Index: 1124434 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.3669. Min Act: -0.0000

Data Index: 26909 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.3930. Min Act: -0.0000

Data Index: 444624 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.3631. Min Act: -0.0000

Data Index: 942484 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2468. Min Act: -0.0000

Data Index: 629680 (The Pile)

Max Activating Token Index: 475

Text #5

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.3039. Min Act: -0.0000

Data Index: 502876 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1398. Min Act: -0.0000

Data Index: 225966 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1462617 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2814. Min Act: -0.0000

Data Index: 112083 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2291. Min Act: -0.0000

Data Index: 851562 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2506. Min Act: -0.0000

Data Index: 147949 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1726. Min Act: -0.0000

Data Index: 913025 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1652. Min Act: -0.0000

Data Index: 986028 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1312629 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1435198 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1320069 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2144. Min Act: -0.0000

Data Index: 1552698 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1012. Min Act: -0.0000

Data Index: 291006 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1534613 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1675677 (The Pile)

Max Activating Token Index: 811