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

Dataset: The Pile

Neuron 437 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: 0.5551. Min Range: -0.5551

Max Act: 0.5551. Min Act: -0.0000

Data Index: 425520 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1722390 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1981034 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4726. Min Act: -0.0000

Data Index: 212123 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1819500 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4840. Min Act: -0.0000

Data Index: 911947 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4154. Min Act: -0.0001

Data Index: 1305500 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4600. Min Act: -0.0000

Data Index: 27478 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1652642 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4002. Min Act: -0.0000

Data Index: 858576 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1445644 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.3726. Min Act: -0.0000

Data Index: 918589 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1351645 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1448189 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.3580. Min Act: -0.0000

Data Index: 389226 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1619693 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1293995 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1388099 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.3337. Min Act: -0.0000

Data Index: 986723 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.2991. Min Act: -0.0000

Data Index: 822851 (The Pile)

Max Activating Token Index: 504