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

Dataset: The Pile

Neuron 1408 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1739993 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1710162 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4535. Min Act: -0.0000

Data Index: 860329 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1324389 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3959. Min Act: 0.0000

Data Index: 1520432 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3790. Min Act: -0.0000

Data Index: 767172 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3824. Min Act: -0.0000

Data Index: 562909 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1376609 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1856874 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1720802 (The Pile)

Max Activating Token Index: 921

Text #10

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1417862 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3984. Min Act: -0.0000

Data Index: 300931 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3664. Min Act: -0.0000

Data Index: 953267 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1299382 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3601. Min Act: 0.0000

Data Index: 1385133 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3642. Min Act: -0.0000

Data Index: 176610 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1099194 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3437. Min Act: -0.0000

Data Index: 426876 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3427. Min Act: -0.0000

Data Index: 449460 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3550. Min Act: -0.0000

Data Index: 312557 (The Pile)

Max Activating Token Index: 681