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

Dataset: The Pile

Neuron 2169 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1116688 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1242023 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1051338 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.1599. Min Act: -0.0000

Data Index: 179338 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.0793. Min Act: -0.0000

Data Index: 887163 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1653286 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.0778. Min Act: -0.0000

Data Index: 881199 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1033466 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9735. Min Act: -0.0000

Data Index: 461979 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1039566 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 1.6446. Min Range: -1.6446

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1074698 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9768. Min Act: -0.0000

Data Index: 83097 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1298730 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1812077 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1786564 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9347. Min Act: -0.0000

Data Index: 377586 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1893505 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1194005 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1088231 (The Pile)

Max Activating Token Index: 419

Text #19

Max Range: 1.6446. Min Range: -1.6446

Max Act: 0.9128. Min Act: -0.0000

Data Index: 281826 (The Pile)

Max Activating Token Index: 359