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

Dataset: The Pile

Neuron 3139 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: 1.8990. Min Range: -1.8990

Max Act: 1.8960. Min Act: -0.0000

Data Index: 1000800 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.8990. Min Act: -0.0000

Data Index: 711086 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.7815. Min Act: 0.0000

Data Index: 1828068 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.8541. Min Act: -0.0000

Data Index: 1044831 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.7263. Min Act: -0.0000

Data Index: 879556 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5591. Min Act: -0.0000

Data Index: 146462 (The Pile)

Max Activating Token Index: 821

Text #6

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.8057. Min Act: -0.0000

Data Index: 1621957 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5657. Min Act: -0.0000

Data Index: 1217703 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4238. Min Act: -0.0000

Data Index: 230255 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.6165. Min Act: -0.0000

Data Index: 849969 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.6067. Min Act: -0.0000

Data Index: 1047104 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.7957. Min Act: -0.0000

Data Index: 825615 (The Pile)

Max Activating Token Index: 928

Text #12

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4856. Min Act: -0.0000

Data Index: 422659 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5615. Min Act: 0.0000

Data Index: 336427 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1609609 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5253. Min Act: 0.0000

Data Index: 1158189 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1411633 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5609. Min Act: -0.0000

Data Index: 182475 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.3796. Min Act: -0.0000

Data Index: 1595507 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4672. Min Act: 0.0000

Data Index: 2890 (The Pile)

Max Activating Token Index: 57