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

Dataset: The Pile

Neuron 4173 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: 1.1903. Min Range: -1.1903

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1963013 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.5812. Min Act: -0.0000

Data Index: 73045 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4886. Min Act: -0.0000

Data Index: 57062 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4464. Min Act: -0.0000

Data Index: 637771 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1159640 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1128713 (The Pile)

Max Activating Token Index: 268

Text #6

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1299591 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4736. Min Act: -0.0000

Data Index: 288822 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1676912 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1231464 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1064577 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1962347 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4069. Min Act: -0.0000

Data Index: 917957 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1218292 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1457800 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.3854. Min Act: -0.0000

Data Index: 3400 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1865484 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1132502 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1940255 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1475394 (The Pile)

Max Activating Token Index: 518