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

Dataset: The Pile

Neuron 1423 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1351287 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3499. Min Act: -0.0000

Data Index: 685432 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1355681 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3296. Min Act: -0.0000

Data Index: 139681 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3131. Min Act: -0.0000

Data Index: 384050 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3541. Min Act: -0.0000

Data Index: 502791 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1019108 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1286262 (The Pile)

Max Activating Token Index: 687

Text #8

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3075. Min Act: -0.0000

Data Index: 627568 (The Pile)

Max Activating Token Index: 172

Text #9

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2839. Min Act: -0.0000

Data Index: 39031 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1628116 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1167732 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2957. Min Act: -0.0001

Data Index: 990038 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3154. Min Act: -0.0000

Data Index: 865958 (The Pile)

Max Activating Token Index: 776

Text #14

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2642. Min Act: -0.0000

Data Index: 657932 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2998. Min Act: -0.0000

Data Index: 78597 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1229551 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2593. Min Act: -0.0000

Data Index: 876607 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2706. Min Act: -0.0001

Data Index: 1907098 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2888. Min Act: -0.0000

Data Index: 140126 (The Pile)

Max Activating Token Index: 396