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

Dataset: The Pile

Neuron 954 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1499924 (The Pile)

Max Activating Token Index: 951

Text #1

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3990. Min Act: -0.0000

Data Index: 819715 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1265815 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3569. Min Act: -0.0000

Data Index: 104305 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1035974 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3428. Min Act: -0.0000

Data Index: 50561 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1542781 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3690. Min Act: -0.0000

Data Index: 891079 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1312304 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1787625 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3262. Min Act: -0.0000

Data Index: 28083 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3480. Min Act: -0.0000

Data Index: 633071 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3682. Min Act: -0.0000

Data Index: 10479 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1070693 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1809507 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1105052 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1673013 (The Pile)

Max Activating Token Index: 274

Text #17

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3465. Min Act: -0.0000

Data Index: 354101 (The Pile)

Max Activating Token Index: 3

Text #18

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3796. Min Act: -0.0000

Data Index: 944409 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1691900 (The Pile)

Max Activating Token Index: 414