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

Dataset: The Pile

Neuron 3214 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1335383 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.4164. Min Act: -0.0000

Data Index: 1737785 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5937. Min Act: -0.0000

Data Index: 1555289 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5153. Min Act: -0.0000

Data Index: 470802 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5541. Min Act: -0.0000

Data Index: 892540 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5563. Min Act: -0.0000

Data Index: 749088 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1955865 (The Pile)

Max Activating Token Index: 5

Text #7

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5391. Min Act: -0.0000

Data Index: 651221 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5296. Min Act: -0.0000

Data Index: 145368 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.5278. Min Act: -0.0000

Data Index: 191706 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.6195. Min Act: -0.0000

Data Index: 1845157 (The Pile)

Max Activating Token Index: 862

Text #11

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1115430 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.4615. Min Act: -0.0000

Data Index: 140537 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1508564 (The Pile)

Max Activating Token Index: 420

Text #14

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1989571 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.3388. Min Act: -0.0000

Data Index: 837272 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1426229 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.4071. Min Act: -0.0000

Data Index: 558018 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1613808 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 1.6195. Min Range: -1.6195

Max Act: 1.3984. Min Act: -0.0000

Data Index: 541991 (The Pile)

Max Activating Token Index: 722