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

Dataset: The Pile

Neuron 1630 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.7101. Min Act: -0.0000

Data Index: 294015 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.9221. Min Act: -0.0000

Data Index: 1663559 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.6948. Min Act: -0.0000

Data Index: 1926073 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.7347. Min Act: -0.0000

Data Index: 1483227 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.4411. Min Act: -0.0000

Data Index: 605507 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.7855. Min Act: -0.0000

Data Index: 428539 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.6115. Min Act: -0.0000

Data Index: 971081 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.3325. Min Act: -0.0000

Data Index: 1510024 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.8729. Min Act: -0.0000

Data Index: 1162411 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.3466. Min Act: -0.0000

Data Index: 1612808 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.4554. Min Act: -0.0000

Data Index: 1772040 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.0602. Min Act: -0.0000

Data Index: 15993 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.8252. Min Act: -0.0000

Data Index: 1999741 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.5289. Min Act: -0.0000

Data Index: 977896 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.3908. Min Act: -0.0000

Data Index: 1772808 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.8309. Min Act: -0.0000

Data Index: 1935355 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.5157. Min Act: -0.0000

Data Index: 861318 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 5.9221. Min Range: -5.9221

Max Act: 4.4463. Min Act: -0.0000

Data Index: 1153120 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.3207. Min Act: -0.0000

Data Index: 198977 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 5.9221. Min Range: -5.9221

Max Act: 5.4056. Min Act: -0.0000

Data Index: 1580613 (The Pile)

Max Activating Token Index: 196