Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2821 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.9572. Min Act: -0.0000

Data Index: 624621 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8086. Min Act: -0.0000

Data Index: 770635 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7888. Min Act: 0.0000

Data Index: 756818 (The Pile)

Max Activating Token Index: 167

Text #3

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8529. Min Act: -0.0000

Data Index: 947577 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1827896 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7005. Min Act: -0.0000

Data Index: 387636 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6891. Min Act: -0.0000

Data Index: 662378 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1486347 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1308666 (The Pile)

Max Activating Token Index: 729

Text #9

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1424807 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5985. Min Act: -0.0000

Data Index: 516090 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5733. Min Act: -0.0000

Data Index: 755419 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1543982 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6112. Min Act: -0.0000

Data Index: 812228 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5472. Min Act: -0.0000

Data Index: 178027 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5485. Min Act: -0.0000

Data Index: 650744 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1103496 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1756178 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1626709 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5703. Min Act: -0.0000

Data Index: 69673 (The Pile)

Max Activating Token Index: 488