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

Dataset: The Pile

Neuron 2517 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1320503 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0723. Min Act: -0.0000

Data Index: 424201 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1169634 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1727418 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1343110 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1917211 (The Pile)

Max Activating Token Index: 310

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0557. Min Act: -0.0000

Data Index: 133536 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0575. Min Act: -0.0000

Data Index: 651722 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0550. Min Act: -0.0000

Data Index: 313 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1934848 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0548. Min Act: -0.0000

Data Index: 189042 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0546. Min Act: -0.0000

Data Index: 978225 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0544. Min Act: -0.0000

Data Index: 990615 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0543. Min Act: -0.0000

Data Index: 199186 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0541. Min Act: -0.0000

Data Index: 846828 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0542. Min Act: -0.0000

Data Index: 620938 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1709665 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0539. Min Act: -0.0000

Data Index: 375519 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1050133 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0535. Min Act: -0.0000

Data Index: 563348 (The Pile)

Max Activating Token Index: 445