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

Dataset: The Pile

Neuron 4509 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: 1.1830. Min Range: -1.1830

Max Act: 1.1830. Min Act: -0.0000

Data Index: 743593 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9795. Min Act: -0.0000

Data Index: 13543 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1508454 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1379832 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 1.1830. Min Range: -1.1830

Max Act: 1.0339. Min Act: -0.0000

Data Index: 689428 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8318. Min Act: -0.0000

Data Index: 141450 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1232681 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9798. Min Act: -0.0000

Data Index: 669324 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1487469 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8679. Min Act: -0.0000

Data Index: 171566 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1902018 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8024. Min Act: -0.0000

Data Index: 649432 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8838. Min Act: -0.0000

Data Index: 751557 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8501. Min Act: -0.0000

Data Index: 764562 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1833236 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1305494 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1994554 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8650. Min Act: -0.0000

Data Index: 114675 (The Pile)

Max Activating Token Index: 847

Text #18

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8174. Min Act: -0.0000

Data Index: 597364 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1715670 (The Pile)

Max Activating Token Index: 919