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

Dataset: The Pile

Neuron 2818 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: 2.7571. Min Range: -2.7571

Max Act: 2.7571. Min Act: -0.0000

Data Index: 110115 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6693. Min Act: -0.0000

Data Index: 469630 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.5562. Min Act: 0.0000

Data Index: 1745711 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.3097. Min Act: -0.0000

Data Index: 1145626 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.3025. Min Act: -0.0000

Data Index: 1623456 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.3789. Min Act: -0.0000

Data Index: 1917138 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.2563. Min Act: -0.0000

Data Index: 38242 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.2668. Min Act: -0.0000

Data Index: 1812683 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.2293. Min Act: -0.0000

Data Index: 1096245 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.0836. Min Act: -0.0000

Data Index: 1444671 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.9423. Min Act: -0.0000

Data Index: 348180 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.1528. Min Act: -0.0000

Data Index: 1562859 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.0045. Min Act: -0.0000

Data Index: 432349 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.9728. Min Act: -0.0000

Data Index: 1042894 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.9400. Min Act: -0.0000

Data Index: 477694 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.8319. Min Act: -0.0000

Data Index: 1921639 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.9162. Min Act: -0.0000

Data Index: 710253 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.7962. Min Act: -0.0000

Data Index: 372890 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.9059. Min Act: -0.0000

Data Index: 109697 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.8015. Min Act: -0.0000

Data Index: 693388 (The Pile)

Max Activating Token Index: 98