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

Dataset: The Pile

Neuron 1597 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: 3.1869. Min Range: -3.1869

Max Act: 3.1869. Min Act: -0.0000

Data Index: 570334 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 3.1869. Min Range: -3.1869

Max Act: 3.0302. Min Act: -0.0000

Data Index: 304561 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 3.1869. Min Range: -3.1869

Max Act: 3.0930. Min Act: -0.0000

Data Index: 532049 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.8978. Min Act: -0.0000

Data Index: 1110354 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.7048. Min Act: -0.0000

Data Index: 417433 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.8256. Min Act: -0.0000

Data Index: 1634636 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.8151. Min Act: -0.0000

Data Index: 1586789 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.9008. Min Act: -0.0000

Data Index: 881693 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.6903. Min Act: -0.0000

Data Index: 337715 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.5655. Min Act: -0.0000

Data Index: 371133 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.6048. Min Act: -0.0000

Data Index: 1659283 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.4550. Min Act: -0.0000

Data Index: 637915 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.7103. Min Act: -0.0000

Data Index: 1406875 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.5738. Min Act: -0.0000

Data Index: 203019 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.3473. Min Act: -0.0000

Data Index: 1934934 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.4658. Min Act: -0.0000

Data Index: 1113213 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.4554. Min Act: -0.0000

Data Index: 935951 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.4596. Min Act: -0.0000

Data Index: 549750 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.3871. Min Act: -0.0000

Data Index: 1015259 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.3633. Min Act: -0.0000

Data Index: 58779 (The Pile)

Max Activating Token Index: 434