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

Dataset: The Pile

Neuron 887 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: 1.9502. Min Range: -1.9502

Max Act: 1.9502. Min Act: -0.0000

Data Index: 734068 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7511. Min Act: -0.0000

Data Index: 519501 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6103. Min Act: -0.0000

Data Index: 1895138 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1295325 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6684. Min Act: -0.0000

Data Index: 656006 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.8254. Min Act: -0.0000

Data Index: 382456 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.8584. Min Act: -0.0000

Data Index: 1067327 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6299. Min Act: -0.0000

Data Index: 1280640 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5372. Min Act: -0.0000

Data Index: 611938 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5161. Min Act: -0.0000

Data Index: 1387818 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5026. Min Act: -0.0000

Data Index: 1187204 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5981. Min Act: -0.0000

Data Index: 452863 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6185. Min Act: -0.0000

Data Index: 953081 (The Pile)

Max Activating Token Index: 699

Text #13

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.4382. Min Act: -0.0000

Data Index: 413486 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5227. Min Act: -0.0000

Data Index: 393408 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5002. Min Act: -0.0000

Data Index: 932094 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.4770. Min Act: -0.0000

Data Index: 142812 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1454957 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.3669. Min Act: -0.0000

Data Index: 199564 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.4426. Min Act: -0.0000

Data Index: 901258 (The Pile)

Max Activating Token Index: 935