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

Dataset: The Pile

Neuron 3362 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.9079. Min Act: -0.0000

Data Index: 686250 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.7702. Min Act: -0.0000

Data Index: 1397886 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.4193. Min Act: -0.0000

Data Index: 788588 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.6494. Min Act: -0.0000

Data Index: 1415908 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.8775. Min Act: -0.0000

Data Index: 44372 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.5671. Min Act: -0.0000

Data Index: 1353965 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 4.0962. Min Range: -4.0962

Max Act: 4.0962. Min Act: -0.0000

Data Index: 1041380 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.7976. Min Act: -0.0000

Data Index: 1081148 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.7497. Min Act: -0.0000

Data Index: 1595405 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 4.0962. Min Range: -4.0962

Max Act: 2.9612. Min Act: -0.0000

Data Index: 59509 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.5894. Min Act: -0.0000

Data Index: 478915 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.2555. Min Act: -0.0000

Data Index: 575933 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.3931. Min Act: -0.0000

Data Index: 338750 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.2936. Min Act: -0.0000

Data Index: 1868507 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.0886. Min Act: -0.0000

Data Index: 22169 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.1439. Min Act: -0.0000

Data Index: 43393 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.1822. Min Act: -0.0000

Data Index: 1232226 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.3381. Min Act: -0.0000

Data Index: 75312 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.5193. Min Act: -0.0000

Data Index: 872405 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 4.0962. Min Range: -4.0962

Max Act: 3.4276. Min Act: -0.0000

Data Index: 1890613 (The Pile)

Max Activating Token Index: 538