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

Dataset: The Pile

Neuron 2087 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.3067. Min Act: -0.0000

Data Index: 930810 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4682. Min Act: -0.0000

Data Index: 841469 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.1827. Min Act: -0.0000

Data Index: 390591 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.2439. Min Act: -0.0000

Data Index: 518042 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1831544 (The Pile)

Max Activating Token Index: 927

Text #5

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.1047. Min Act: -0.0000

Data Index: 1434403 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1948129 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 1.4682. Min Range: -1.4682

Max Act: 0.7789. Min Act: -0.0000

Data Index: 453358 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 1.4682. Min Range: -1.4682

Max Act: 0.9704. Min Act: -0.0000

Data Index: 712033 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 1.4682. Min Range: -1.4682

Max Act: 0.8346. Min Act: -0.0000

Data Index: 304837 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 1.4682. Min Range: -1.4682

Max Act: 0.9547. Min Act: -0.0000

Data Index: 596263 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 1.4682. Min Range: -1.4682

Max Act: 0.9564. Min Act: -0.0000

Data Index: 563367 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.0952. Min Act: -0.0000

Data Index: 858881 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1291669 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 1.4682. Min Range: -1.4682

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1454899 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 1.4682. Min Range: -1.4682

Max Act: 0.9756. Min Act: -0.0000

Data Index: 635821 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.0131. Min Act: -0.0000

Data Index: 778082 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 1.4682. Min Range: -1.4682

Max Act: 0.9612. Min Act: -0.0000

Data Index: 284899 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1121482 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1912200 (The Pile)

Max Activating Token Index: 872