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

Dataset: The Pile

Neuron 492 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: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1174654 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6918. Min Act: -0.0000

Data Index: 708086 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6679. Min Act: -0.0000

Data Index: 989499 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6262. Min Act: -0.0000

Data Index: 21933 (The Pile)

Max Activating Token Index: 633

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1493082 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6859. Min Act: -0.0000

Data Index: 362237 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5819. Min Act: -0.0000

Data Index: 103298 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1295687 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6186. Min Act: -0.0000

Data Index: 699974 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6078. Min Act: -0.0000

Data Index: 106756 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1976838 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5778. Min Act: -0.0000

Data Index: 887555 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6508. Min Act: -0.0000

Data Index: 601809 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1796969 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1421170 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1777728 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5553. Min Act: -0.0000

Data Index: 405514 (The Pile)

Max Activating Token Index: 575

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5786. Min Act: -0.0000

Data Index: 74927 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1649947 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1720000 (The Pile)

Max Activating Token Index: 1012