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

Dataset: The Pile

Neuron 121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1412725 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1035835 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1584191 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3426. Min Act: -0.0000

Data Index: 391839 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3543. Min Act: -0.0000

Data Index: 627889 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1802497 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1450623 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3115. Min Act: -0.0000

Data Index: 495612 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1721026 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1449071 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1004384 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1625185 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2939. Min Act: 0.0000

Data Index: 330232 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1613555 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1393924 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1167669 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2895. Min Act: -0.0000

Data Index: 512465 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1173634 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3263. Min Act: -0.0000

Data Index: 523366 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2729. Min Act: -0.0000

Data Index: 833413 (The Pile)

Max Activating Token Index: 276