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

Dataset: The Pile

Neuron 657 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.7183. Min Act: -0.0000

Data Index: 1509718 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.4741. Min Act: -0.0000

Data Index: 1441061 (The Pile)

Max Activating Token Index: 268

Text #2

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.3097. Min Act: -0.0000

Data Index: 99266 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1114437 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.3317. Min Act: -0.0000

Data Index: 1513139 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1008602 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1052638 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1925697 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.1813. Min Act: -0.0000

Data Index: 677463 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1821538 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1407043 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1141209 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.0910. Min Act: -0.0000

Data Index: 445449 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1425099 (The Pile)

Max Activating Token Index: 917

Text #14

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1844250 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 1.7183. Min Range: -1.7183

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1372896 (The Pile)

Max Activating Token Index: 732

Text #16

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.0575. Min Act: -0.0000

Data Index: 911587 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.0476. Min Act: -0.0000

Data Index: 136676 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.7183. Min Range: -1.7183

Max Act: 0.8952. Min Act: -0.0000

Data Index: 536028 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 1.7183. Min Range: -1.7183

Max Act: 1.0417. Min Act: -0.0000

Data Index: 426733 (The Pile)

Max Activating Token Index: 193