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

Dataset: The Pile

Neuron 1045 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.3665. Min Act: -0.0000

Data Index: 790608 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2475. Min Act: -0.0000

Data Index: 1075369 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1863. Min Act: -0.0000

Data Index: 911121 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0285. Min Act: -0.0000

Data Index: 660518 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0859. Min Act: -0.0000

Data Index: 12857 (The Pile)

Max Activating Token Index: 633

Text #5

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0396. Min Act: -0.0000

Data Index: 449823 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2182. Min Act: -0.0000

Data Index: 362508 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.9895. Min Act: -0.0000

Data Index: 157422 (The Pile)

Max Activating Token Index: 67

Text #8

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1514876 (The Pile)

Max Activating Token Index: 506

Text #9

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1763576 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.8402. Min Act: -0.0000

Data Index: 959491 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.7952. Min Act: -0.0000

Data Index: 616640 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.9519. Min Act: -0.0000

Data Index: 586809 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1114660 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1650908 (The Pile)

Max Activating Token Index: 852

Text #15

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1530561 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.7544. Min Act: 0.0000

Data Index: 1518536 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1432373 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1724102 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1998935 (The Pile)

Max Activating Token Index: 64