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

Dataset: The Pile

Neuron 1330 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: 5.5278. Min Range: -5.5278

Max Act: 5.5278. Min Act: -0.0000

Data Index: 37700 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 5.5278. Min Range: -5.5278

Max Act: 5.3046. Min Act: -0.0000

Data Index: 1619066 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 5.5278. Min Range: -5.5278

Max Act: 4.6324. Min Act: -0.0000

Data Index: 788716 (The Pile)

Max Activating Token Index: 45

Text #3

Max Range: 5.5278. Min Range: -5.5278

Max Act: 4.7689. Min Act: -0.0000

Data Index: 1951385 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 5.5278. Min Range: -5.5278

Max Act: 4.1449. Min Act: -0.0000

Data Index: 929031 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 5.5278. Min Range: -5.5278

Max Act: 3.9243. Min Act: -0.0000

Data Index: 140366 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 5.5278. Min Range: -5.5278

Max Act: 3.1063. Min Act: -0.0000

Data Index: 1364587 (The Pile)

Max Activating Token Index: 625

Text #7

Max Range: 5.5278. Min Range: -5.5278

Max Act: 3.5176. Min Act: -0.0000

Data Index: 483435 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 5.5278. Min Range: -5.5278

Max Act: 3.1679. Min Act: -0.0000

Data Index: 803361 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 5.5278. Min Range: -5.5278

Max Act: 2.8409. Min Act: -0.0000

Data Index: 1790142 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 5.5278. Min Range: -5.5278

Max Act: 2.7128. Min Act: -0.0000

Data Index: 497464 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 5.5278. Min Range: -5.5278

Max Act: 2.7666. Min Act: -0.0000

Data Index: 865072 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 5.5278. Min Range: -5.5278

Max Act: 3.0212. Min Act: -0.0000

Data Index: 322972 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 5.5278. Min Range: -5.5278

Max Act: 3.3390. Min Act: -0.0000

Data Index: 1540137 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 5.5278. Min Range: -5.5278

Max Act: 3.1401. Min Act: -0.0000

Data Index: 1827353 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 5.5278. Min Range: -5.5278

Max Act: 2.7359. Min Act: -0.0000

Data Index: 1742500 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 5.5278. Min Range: -5.5278

Max Act: 2.8993. Min Act: -0.0000

Data Index: 888368 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 5.5278. Min Range: -5.5278

Max Act: 3.0080. Min Act: -0.0000

Data Index: 1641892 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 5.5278. Min Range: -5.5278

Max Act: 2.6925. Min Act: -0.0000

Data Index: 257021 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 5.5278. Min Range: -5.5278

Max Act: 2.2758. Min Act: -0.0000

Data Index: 145882 (The Pile)

Max Activating Token Index: 749