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

Dataset: The Pile

Neuron 4001 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1641964 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6727. Min Act: -0.0000

Data Index: 897465 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1466714 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1276741 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6192. Min Act: -0.0000

Data Index: 280773 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6158. Min Act: -0.0000

Data Index: 559770 (The Pile)

Max Activating Token Index: 467

Text #6

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6368. Min Act: -0.0000

Data Index: 152877 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6089. Min Act: -0.0000

Data Index: 952103 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5848. Min Act: -0.0000

Data Index: 587313 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1793109 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1999847 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5947. Min Act: -0.0000

Data Index: 211982 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1407747 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1811454 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5722. Min Act: -0.0000

Data Index: 439169 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1420150 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1197951 (The Pile)

Max Activating Token Index: 695

Text #17

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1228943 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5760. Min Act: -0.0000

Data Index: 981355 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1209565 (The Pile)

Max Activating Token Index: 246