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

Dataset: The Pile

Neuron 378 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: 0.4219. Min Range: -0.4219

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1517534 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4025. Min Act: -0.0000

Data Index: 173326 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4176. Min Act: -0.0000

Data Index: 681191 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1492392 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1221899 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3962. Min Act: -0.0000

Data Index: 174196 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1651925 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1433628 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1104542 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1215970 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1521011 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3995. Min Act: -0.0000

Data Index: 815626 (The Pile)

Max Activating Token Index: 898

Text #12

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3608. Min Act: -0.0000

Data Index: 65252 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3595. Min Act: -0.0000

Data Index: 610223 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1633215 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1142204 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1809472 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3752. Min Act: -0.0000

Data Index: 793322 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3722. Min Act: -0.0000

Data Index: 354020 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1593122 (The Pile)

Max Activating Token Index: 194