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

Dataset: The Pile

Neuron 3500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.3944. Min Act: -0.0000

Data Index: 617216 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2656. Min Act: -0.0000

Data Index: 79810 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1675009 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1887600 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2501. Min Act: -0.0000

Data Index: 949756 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1379867 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1392925 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1079121 (The Pile)

Max Activating Token Index: 464

Text #8

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1748775 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1564997 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1028898 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1734. Min Act: 0.0000

Data Index: 567031 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1074242 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1626. Min Act: -0.0000

Data Index: 140143 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1184030 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1651. Min Act: 0.0000

Data Index: 1460506 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1395294 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1388854 (The Pile)

Max Activating Token Index: 954

Text #18

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1790444 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.1590. Min Act: -0.0000

Data Index: 787976 (The Pile)

Max Activating Token Index: 448