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

Dataset: The Pile

Neuron 899 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.5869. Min Act: -0.0000

Data Index: 549113 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.5239. Min Act: -0.0000

Data Index: 689130 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.1631. Min Act: -0.0000

Data Index: 671119 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.4598. Min Act: -0.0000

Data Index: 1412025 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.4200. Min Act: -0.0000

Data Index: 1961738 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.4088. Min Act: -0.0000

Data Index: 785762 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.2446. Min Act: -0.0000

Data Index: 334512 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.3768. Min Act: -0.0000

Data Index: 1299783 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.3186. Min Act: -0.0000

Data Index: 227723 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.4748. Min Act: -0.0000

Data Index: 1628691 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.0602. Min Act: -0.0000

Data Index: 791979 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 3.5869. Min Range: -3.5869

Max Act: 2.9605. Min Act: -0.0000

Data Index: 1278972 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.0973. Min Act: -0.0000

Data Index: 214988 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 3.5869. Min Range: -3.5869

Max Act: 2.9289. Min Act: -0.0000

Data Index: 406455 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 3.5869. Min Range: -3.5869

Max Act: 2.9311. Min Act: -0.0000

Data Index: 913440 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.0569. Min Act: -0.0000

Data Index: 966982 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.0537. Min Act: -0.0000

Data Index: 1775501 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.0388. Min Act: -0.0000

Data Index: 315184 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.0205. Min Act: -0.0000

Data Index: 687336 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 3.5869. Min Range: -3.5869

Max Act: 3.1371. Min Act: -0.0000

Data Index: 627541 (The Pile)

Max Activating Token Index: 155