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

Dataset: The Pile

Neuron 157 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4419. Min Act: -0.0000

Data Index: 942461 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1672964 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1229082 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4028. Min Act: -0.0000

Data Index: 612235 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4044. Min Act: -0.0000

Data Index: 638717 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3685. Min Act: -0.0000

Data Index: 44488 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1746614 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1273983 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3826. Min Act: -0.0000

Data Index: 90126 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1619843 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1003008 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3494. Min Act: -0.0000

Data Index: 591355 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3629. Min Act: -0.0000

Data Index: 348133 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1909647 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3587. Min Act: 0.0000

Data Index: 162477 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3549. Min Act: -0.0000

Data Index: 794185 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3734. Min Act: -0.0000

Data Index: 758899 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3377. Min Act: -0.0000

Data Index: 934199 (The Pile)

Max Activating Token Index: 563

Text #18

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1834689 (The Pile)

Max Activating Token Index: 840

Text #19

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3470. Min Act: -0.0000

Data Index: 63961 (The Pile)

Max Activating Token Index: 70