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

Dataset: The Pile

Neuron 3484 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: 1.9946. Min Range: -1.9946

Max Act: 1.9946. Min Act: -0.0000

Data Index: 290771 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.4129. Min Act: -0.0000

Data Index: 203467 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.4905. Min Act: -0.0000

Data Index: 409223 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.3554. Min Act: -0.0000

Data Index: 127486 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.3692. Min Act: -0.0000

Data Index: 752614 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1203663 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.1787. Min Act: -0.0000

Data Index: 926549 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1619005 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.1380. Min Act: -0.0000

Data Index: 17006 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0925. Min Act: -0.0000

Data Index: 58418 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.2011. Min Act: -0.0000

Data Index: 1667267 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1987975 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1575947 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0967. Min Act: -0.0000

Data Index: 570038 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0669. Min Act: -0.0000

Data Index: 434273 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1582175 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1438895 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0785. Min Act: -0.0000

Data Index: 566936 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0417. Min Act: -0.0000

Data Index: 607283 (The Pile)

Max Activating Token Index: 988

Text #19

Max Range: 1.9946. Min Range: -1.9946

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1759753 (The Pile)

Max Activating Token Index: 462