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

Dataset: The Pile

Neuron 1992 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: 0.5249. Min Range: -0.5249

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1419864 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1542173 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1807799 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4331. Min Act: -0.0000

Data Index: 374531 (The Pile)

Max Activating Token Index: 554

Text #4

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4599. Min Act: -0.0000

Data Index: 540713 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1821161 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1372212 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1891417 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3948. Min Act: -0.0000

Data Index: 281736 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4433. Min Act: -0.0000

Data Index: 913561 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3705. Min Act: -0.0000

Data Index: 901658 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1979449 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4016. Min Act: -0.0000

Data Index: 952745 (The Pile)

Max Activating Token Index: 622

Text #13

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1082028 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1172670 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3747. Min Act: -0.0000

Data Index: 272033 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1793360 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1817208 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3918. Min Act: -0.0000

Data Index: 20069 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3843. Min Act: -0.0000

Data Index: 638481 (The Pile)

Max Activating Token Index: 566