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

Dataset: The Pile

Neuron 2785 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: 0.6098. Min Range: -0.6098

Max Act: 0.6098. Min Act: -0.0000

Data Index: 761166 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1898787 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1675186 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1818624 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1681204 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1044206 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1686886 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5833. Min Act: -0.0000

Data Index: 558980 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4993. Min Act: -0.0000

Data Index: 874873 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1845005 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5208. Min Act: -0.0000

Data Index: 819358 (The Pile)

Max Activating Token Index: 229

Text #11

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1045833 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1701061 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1829922 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1857855 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1040791 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1254282 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4923. Min Act: -0.0000

Data Index: 786659 (The Pile)

Max Activating Token Index: 977

Text #18

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4749. Min Act: -0.0000

Data Index: 217894 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4998. Min Act: -0.0000

Data Index: 319313 (The Pile)

Max Activating Token Index: 131