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

Dataset: The Pile

Neuron 3634 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: 3.9653. Min Range: -3.9653

Max Act: 3.9302. Min Act: -0.0000

Data Index: 207501 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.7984. Min Act: -0.0000

Data Index: 152751 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.7122. Min Act: -0.0000

Data Index: 731901 (The Pile)

Max Activating Token Index: 838

Text #3

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.9653. Min Act: -0.0000

Data Index: 1741898 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.4014. Min Act: -0.0000

Data Index: 867181 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.5504. Min Act: -0.0000

Data Index: 838222 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.4972. Min Act: -0.0000

Data Index: 462409 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.5106. Min Act: -0.0000

Data Index: 1856029 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.2094. Min Act: -0.0000

Data Index: 1212784 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.3521. Min Act: -0.0000

Data Index: 1354484 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.3321. Min Act: -0.0000

Data Index: 469557 (The Pile)

Max Activating Token Index: 533

Text #11

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.1281. Min Act: -0.0000

Data Index: 984506 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.1830. Min Act: -0.0000

Data Index: 170453 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.1440. Min Act: -0.0000

Data Index: 1446290 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 3.9653. Min Range: -3.9653

Max Act: 2.9965. Min Act: -0.0000

Data Index: 1425601 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.1141. Min Act: -0.0000

Data Index: 988128 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.2206. Min Act: -0.0000

Data Index: 578601 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.4289. Min Act: -0.0000

Data Index: 1697130 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.0728. Min Act: -0.0000

Data Index: 40784 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.0502. Min Act: -0.0000

Data Index: 1867134 (The Pile)

Max Activating Token Index: 581