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

Dataset: The Pile

Neuron 924 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: 1.0473. Min Range: -1.0473

Max Act: 1.0405. Min Act: -0.0000

Data Index: 344930 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 1.0473. Min Range: -1.0473

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1324195 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 1.0473. Min Range: -1.0473

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1619848 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.9363. Min Act: -0.0000

Data Index: 256562 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1294278 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1255082 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1046063 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8621. Min Act: -0.0000

Data Index: 292732 (The Pile)

Max Activating Token Index: 287

Text #8

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1791896 (The Pile)

Max Activating Token Index: 772

Text #9

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.9085. Min Act: -0.0000

Data Index: 499975 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8472. Min Act: -0.0000

Data Index: 739474 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1514811 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8313. Min Act: -0.0000

Data Index: 962042 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1989594 (The Pile)

Max Activating Token Index: 756

Text #14

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1309213 (The Pile)

Max Activating Token Index: 788

Text #15

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1012181 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1088006 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1285124 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1905203 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8602. Min Act: -0.0000

Data Index: 164726 (The Pile)

Max Activating Token Index: 267