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

Dataset: The Pile

Neuron 3597 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: 1.9304. Min Range: -1.9304

Max Act: 1.9304. Min Act: -0.0000

Data Index: 1341280 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.9104. Min Act: -0.0000

Data Index: 696415 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.8053. Min Act: -0.0000

Data Index: 1573405 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.5628. Min Act: -0.0000

Data Index: 641702 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.5440. Min Act: -0.0000

Data Index: 1829330 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.6408. Min Act: -0.0000

Data Index: 365830 (The Pile)

Max Activating Token Index: 314

Text #6

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.7055. Min Act: -0.0000

Data Index: 1649400 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.4965. Min Act: -0.0000

Data Index: 47787 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.7861. Min Act: -0.0000

Data Index: 684299 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.4932. Min Act: -0.0000

Data Index: 298077 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.6729. Min Act: -0.0000

Data Index: 1552508 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.6694. Min Act: -0.0000

Data Index: 1451872 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1255513 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.5321. Min Act: -0.0000

Data Index: 651523 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1979674 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.5139. Min Act: -0.0000

Data Index: 483553 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.5077. Min Act: -0.0000

Data Index: 59704 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.4993. Min Act: -0.0000

Data Index: 698147 (The Pile)

Max Activating Token Index: 420

Text #18

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.6555. Min Act: -0.0000

Data Index: 942140 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 1.9304. Min Range: -1.9304

Max Act: 1.4639. Min Act: -0.0000

Data Index: 182847 (The Pile)

Max Activating Token Index: 877