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

Dataset: The Pile

Neuron 481 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: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1989792 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0711. Min Act: -0.0000

Data Index: 580538 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1304443 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0668. Min Act: -0.0000

Data Index: 893707 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0691. Min Act: -0.0000

Data Index: 339173 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0679. Min Act: -0.0000

Data Index: 646459 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0681. Min Act: -0.0000

Data Index: 726148 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1426797 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0599. Min Act: -0.0000

Data Index: 488446 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0613. Min Act: -0.0000

Data Index: 270002 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1974189 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1248377 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0517. Min Act: -0.0000

Data Index: 141473 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0527. Min Act: -0.0000

Data Index: 672188 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1572208 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1110674 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0560. Min Act: -0.0000

Data Index: 960410 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1529276 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0509. Min Act: -0.0000

Data Index: 164419 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0525. Min Act: -0.0000

Data Index: 966900 (The Pile)

Max Activating Token Index: 7