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

Dataset: The Pile

Neuron 2724 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8879. Min Act: -0.0000

Data Index: 431765 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8346. Min Act: -0.0000

Data Index: 876200 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8254. Min Act: -0.0000

Data Index: 197314 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1422484 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7412. Min Act: -0.0000

Data Index: 671535 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1535220 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1004076 (The Pile)

Max Activating Token Index: 7

Text #7

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1414489 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1160694 (The Pile)

Max Activating Token Index: 4

Text #9

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7082. Min Act: -0.0000

Data Index: 533287 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5676. Min Act: -0.0000

Data Index: 6978 (The Pile)

Max Activating Token Index: 950

Text #11

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1633492 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6192. Min Act: -0.0000

Data Index: 63183 (The Pile)

Max Activating Token Index: 4

Text #13

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5911. Min Act: -0.0000

Data Index: 20748 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6061. Min Act: -0.0000

Data Index: 581889 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5812. Min Act: -0.0000

Data Index: 623712 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6207. Min Act: -0.0000

Data Index: 518017 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6957. Min Act: -0.0000

Data Index: 802761 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6409. Min Act: -0.0000

Data Index: 948950 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1261070 (The Pile)

Max Activating Token Index: 5