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

Dataset: The Pile

Neuron 4620 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: 5.1718. Min Range: -5.1718

Max Act: 5.1718. Min Act: -0.0000

Data Index: 399502 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.6098. Min Act: -0.0000

Data Index: 443194 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.7677. Min Act: -0.0000

Data Index: 836243 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 5.1718. Min Range: -5.1718

Max Act: 5.1480. Min Act: -0.0000

Data Index: 1624008 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.6478. Min Act: -0.0000

Data Index: 1185622 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.7850. Min Act: -0.0000

Data Index: 1978354 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.6166. Min Act: -0.0000

Data Index: 885401 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.0112. Min Act: -0.0000

Data Index: 1689864 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 5.1718. Min Range: -5.1718

Max Act: 3.9783. Min Act: -0.0000

Data Index: 56448 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.6953. Min Act: -0.0000

Data Index: 1318527 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.4687. Min Act: -0.0000

Data Index: 450346 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.3928. Min Act: -0.0000

Data Index: 744960 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.0763. Min Act: -0.0000

Data Index: 282114 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.7198. Min Act: -0.0000

Data Index: 163111 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.0587. Min Act: -0.0000

Data Index: 267940 (The Pile)

Max Activating Token Index: 902

Text #15

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.3061. Min Act: -0.0000

Data Index: 1869226 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.1645. Min Act: -0.0000

Data Index: 387629 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.1403. Min Act: -0.0000

Data Index: 367445 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.2257. Min Act: -0.0000

Data Index: 30657 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 5.1718. Min Range: -5.1718

Max Act: 4.1803. Min Act: -0.0000

Data Index: 359126 (The Pile)

Max Activating Token Index: 395