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

Dataset: The Pile

Neuron 81 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: 0.6019. Min Range: -0.6019

Max Act: 0.6019. Min Act: -0.0000

Data Index: 387473 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1531049 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4935. Min Act: -0.0000

Data Index: 684051 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4876. Min Act: -0.0000

Data Index: 108560 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1398095 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3733. Min Act: -0.0000

Data Index: 30077 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4617. Min Act: 0.0000

Data Index: 327702 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4636. Min Act: -0.0000

Data Index: 356059 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1941381 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4702. Min Act: -0.0000

Data Index: 635485 (The Pile)

Max Activating Token Index: 375

Text #10

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4170. Min Act: -0.0000

Data Index: 204531 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4322. Min Act: -0.0000

Data Index: 973932 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1379537 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3811. Min Act: -0.0000

Data Index: 40070 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1879234 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1068071 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3599. Min Act: -0.0000

Data Index: 505504 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3101. Min Act: -0.0000

Data Index: 200771 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3537. Min Act: -0.0000

Data Index: 923078 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3747. Min Act: -0.0000

Data Index: 116448 (The Pile)

Max Activating Token Index: 828