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

Dataset: The Pile

Neuron 1593 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: 0.6108. Min Range: -0.6108

Max Act: 0.6080. Min Act: -0.0000

Data Index: 362505 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1397797 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1169160 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1848839 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4699. Min Act: -0.0000

Data Index: 202591 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4551. Min Act: -0.0000

Data Index: 990303 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1617093 (The Pile)

Max Activating Token Index: 539

Text #7

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1474400 (The Pile)

Max Activating Token Index: 731

Text #8

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1264327 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4333. Min Act: -0.0000

Data Index: 472557 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1570480 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1304576 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4497. Min Act: -0.0000

Data Index: 662486 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3944. Min Act: -0.0000

Data Index: 324977 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1904443 (The Pile)

Max Activating Token Index: 117

Text #15

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4149. Min Act: -0.0000

Data Index: 43296 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1432899 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3662. Min Act: -0.0000

Data Index: 394400 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1851037 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1427592 (The Pile)

Max Activating Token Index: 542