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

Dataset: The Pile

Neuron 248 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.7476. Min Act: -0.0000

Data Index: 1182103 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1290584 (The Pile)

Max Activating Token Index: 809

Text #2

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.6012. Min Act: -0.0000

Data Index: 299910 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.4475. Min Act: -0.0000

Data Index: 838331 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3832. Min Act: -0.0000

Data Index: 1590626 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3695. Min Act: -0.0000

Data Index: 190868 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.4355. Min Act: -0.0000

Data Index: 348357 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.4000. Min Act: -0.0000

Data Index: 178973 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1705180 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3622. Min Act: -0.0000

Data Index: 1465496 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3468. Min Act: -0.0000

Data Index: 273354 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3358. Min Act: -0.0000

Data Index: 236650 (The Pile)

Max Activating Token Index: 656

Text #12

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1092187 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3071. Min Act: -0.0000

Data Index: 936767 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1984008 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2233. Min Act: -0.0000

Data Index: 698487 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1743555 (The Pile)

Max Activating Token Index: 250

Text #17

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1752763 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2776. Min Act: -0.0000

Data Index: 353593 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1141813 (The Pile)

Max Activating Token Index: 215