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

Dataset: The Pile

Neuron 2195 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1181652 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1298874 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1816653 (The Pile)

Max Activating Token Index: 559

Text #3

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2155. Min Act: -0.0000

Data Index: 387886 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1997. Min Act: -0.0000

Data Index: 224526 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1031781 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1913. Min Act: -0.0000

Data Index: 84269 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1891. Min Act: -0.0000

Data Index: 31861 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1841590 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1854. Min Act: -0.0000

Data Index: 496235 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1505995 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1781. Min Act: -0.0000

Data Index: 972518 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1586704 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1678. Min Act: -0.0000

Data Index: 839923 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1731. Min Act: -0.0000

Data Index: 38382 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1131443 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1666. Min Act: -0.0000

Data Index: 561151 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1078651 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1687. Min Act: -0.0000

Data Index: 424438 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1625397 (The Pile)

Max Activating Token Index: 492