Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1488160 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1905864 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1397. Min Act: -0.0000

Data Index: 796471 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1266. Min Act: -0.0000

Data Index: 1265816 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1088069 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0635. Min Act: -0.0000

Data Index: 829919 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0935. Min Act: -0.0000

Data Index: 203827 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0881. Min Act: -0.0000

Data Index: 38987 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1668446 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0456. Min Act: -0.0000

Data Index: 146876 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0841. Min Act: -0.0000

Data Index: 881768 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0769. Min Act: -0.0000

Data Index: 840824 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0120. Min Act: -0.0000

Data Index: 606515 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1020162 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1473085 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1389790 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9945. Min Act: -0.0000

Data Index: 607535 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0128. Min Act: -0.0000

Data Index: 587516 (The Pile)

Max Activating Token Index: 459

Text #18

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1066606 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9477. Min Act: -0.0000

Data Index: 98521 (The Pile)

Max Activating Token Index: 530