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

Dataset: The Pile

Neuron 821 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1081882 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7622. Min Act: -0.0000

Data Index: 707230 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6496. Min Act: -0.0000

Data Index: 763699 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7879. Min Act: -0.0000

Data Index: 517800 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1455820 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6440. Min Act: -0.0000

Data Index: 229730 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6809. Min Act: -0.0000

Data Index: 715551 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1659891 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1999919 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1197745 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1551387 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1529340 (The Pile)

Max Activating Token Index: 643

Text #12

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6368. Min Act: -0.0000

Data Index: 192790 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1650290 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6256. Min Act: -0.0000

Data Index: 378139 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1443322 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1612563 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6029. Min Act: -0.0000

Data Index: 528710 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.5524. Min Act: -0.0000

Data Index: 34573 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.4658. Min Act: -0.0000

Data Index: 681205 (The Pile)

Max Activating Token Index: 956