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

Dataset: The Pile

Neuron 1985 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: 1.2259. Min Range: -1.2259

Max Act: 1.2259. Min Act: -0.0000

Data Index: 906971 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1764608 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.7438. Min Act: -0.0000

Data Index: 595221 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1005935 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1888539 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.6277. Min Act: -0.0000

Data Index: 975158 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.6474. Min Act: -0.0000

Data Index: 814093 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1230539 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5869. Min Act: -0.0000

Data Index: 974641 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5789. Min Act: -0.0000

Data Index: 628086 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5653. Min Act: -0.0000

Data Index: 21810 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5631. Min Act: -0.0000

Data Index: 545518 (The Pile)

Max Activating Token Index: 328

Text #12

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1904143 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5202. Min Act: 0.0000

Data Index: 673295 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5131. Min Act: 0.0000

Data Index: 1616807 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5430. Min Act: -0.0000

Data Index: 574137 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5387. Min Act: -0.0000

Data Index: 13226 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5356. Min Act: -0.0000

Data Index: 274035 (The Pile)

Max Activating Token Index: 830

Text #18

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1976728 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1127443 (The Pile)

Max Activating Token Index: 120