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

Dataset: The Pile

Neuron 518 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: 0.0681. Min Range: -0.0681

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1502667 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1205297 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1992585 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0600. Min Act: -0.0000

Data Index: 276454 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0628. Min Act: -0.0000

Data Index: 365858 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1918668 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0595. Min Act: -0.0001

Data Index: 736466 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1326429 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0566. Min Act: -0.0000

Data Index: 371433 (The Pile)

Max Activating Token Index: 150

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0527. Min Act: -0.0000

Data Index: 117526 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0501. Min Act: -0.0000

Data Index: 713064 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0527. Min Act: -0.0000

Data Index: 225068 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1753040 (The Pile)

Max Activating Token Index: 725

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1930515 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1222084 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0539. Min Act: -0.0000

Data Index: 569679 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0465. Min Act: -0.0000

Data Index: 224897 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1068840 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0501. Min Act: -0.0000

Data Index: 245784 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0496. Min Act: -0.0000

Data Index: 396262 (The Pile)

Max Activating Token Index: 503