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

Dataset: The Pile

Neuron 4572 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: 0.6176. Min Range: -0.6176

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1201198 (The Pile)

Max Activating Token Index: 612

Text #1

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.6115. Min Act: -0.0000

Data Index: 815142 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1184653 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5153. Min Act: -0.0000

Data Index: 713936 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1563335 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1794279 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4685. Min Act: -0.0000

Data Index: 210322 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4593. Min Act: -0.0000

Data Index: 966532 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4098. Min Act: -0.0000

Data Index: 989408 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1647718 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1785848 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1657249 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1702395 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1547173 (The Pile)

Max Activating Token Index: 635

Text #14

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.3781. Min Act: -0.0000

Data Index: 771447 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4019. Min Act: -0.0000

Data Index: 683528 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1893654 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1616590 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1789084 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.3637. Min Act: -0.0000

Data Index: 107024 (The Pile)

Max Activating Token Index: 609