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

Dataset: The Pile

Neuron 2702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.9883. Min Act: -0.0000

Data Index: 539253 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.7065. Min Act: -0.0000

Data Index: 960224 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.8442. Min Act: -0.0000

Data Index: 410535 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.9242. Min Act: -0.0000

Data Index: 1168982 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.7697. Min Act: -0.0000

Data Index: 748572 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.7777. Min Act: -0.0000

Data Index: 1391659 (The Pile)

Max Activating Token Index: 997

Text #6

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.7903. Min Act: -0.0000

Data Index: 481064 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.5671. Min Act: -0.0000

Data Index: 524556 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.6516. Min Act: -0.0000

Data Index: 1954117 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1139376 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.7385. Min Act: -0.0000

Data Index: 1888571 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.6042. Min Act: -0.0000

Data Index: 1172892 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.6611. Min Act: -0.0000

Data Index: 800773 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.5678. Min Act: -0.0000

Data Index: 1816302 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.6550. Min Act: -0.0000

Data Index: 1317927 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.5913. Min Act: -0.0000

Data Index: 1099466 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.5139. Min Act: -0.0000

Data Index: 333839 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.6559. Min Act: -0.0000

Data Index: 1874055 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.5869. Min Act: -0.0000

Data Index: 620145 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 1.9883. Min Range: -1.9883

Max Act: 1.5792. Min Act: -0.0000

Data Index: 910185 (The Pile)

Max Activating Token Index: 443