Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.8192. Min Act: -0.0000

Data Index: 289428 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7522. Min Act: -0.0000

Data Index: 725237 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.8038. Min Act: -0.0000

Data Index: 377077 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7803. Min Act: -0.0000

Data Index: 370667 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7736. Min Act: -0.0000

Data Index: 529579 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.8550. Min Act: -0.0000

Data Index: 770188 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1264736 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7324. Min Act: -0.0000

Data Index: 875638 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1222041 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1075739 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1963789 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6684. Min Act: -0.0000

Data Index: 696498 (The Pile)

Max Activating Token Index: 265

Text #12

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1810959 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6092. Min Act: -0.0000

Data Index: 235464 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6288. Min Act: -0.0000

Data Index: 925424 (The Pile)

Max Activating Token Index: 904

Text #15

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1784389 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5923. Min Act: -0.0000

Data Index: 851599 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5500. Min Act: -0.0000

Data Index: 823844 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5541. Min Act: -0.0000

Data Index: 633170 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5765. Min Act: -0.0000

Data Index: 783880 (The Pile)

Max Activating Token Index: 790