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

Dataset: The Pile

Neuron 1584 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0444. Min Act: -0.0000

Data Index: 1929768 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 1052872 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 334375 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1079099 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 406483 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 16845 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 740556 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 686751 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 418810 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 198503 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 906376 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 189093 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 285838 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 873770 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 970432 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 954323 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 948445 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 604905 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: 0.0000

Data Index: 935415 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0438. Min Act: -0.0000

Data Index: 427569 (The Pile)

Max Activating Token Index: 1