Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 72 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1072043 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1360076 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3607. Min Act: -0.0000

Data Index: 633826 (The Pile)

Max Activating Token Index: 411

Text #3

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1235604 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3032. Min Act: -0.0000

Data Index: 38085 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3277. Min Act: -0.0000

Data Index: 173020 (The Pile)

Max Activating Token Index: 376

Text #6

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3497. Min Act: -0.0000

Data Index: 111651 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3083. Min Act: -0.0000

Data Index: 800715 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1533300 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2997. Min Act: -0.0000

Data Index: 321427 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1390050 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1423206 (The Pile)

Max Activating Token Index: 229

Text #12

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2782. Min Act: -0.0000

Data Index: 156177 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3026. Min Act: -0.0000

Data Index: 294015 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1845128 (The Pile)

Max Activating Token Index: 634

Text #15

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1807780 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1597591 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1142874 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1305300 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2604. Min Act: -0.0000

Data Index: 198712 (The Pile)

Max Activating Token Index: 426