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

Dataset: The Pile

Neuron 4752 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1211104 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1757886 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.2158. Min Act: -0.0000

Data Index: 662969 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1940706 (The Pile)

Max Activating Token Index: 459

Text #4

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0555. Min Act: -0.0000

Data Index: 617592 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0457. Min Act: -0.0000

Data Index: 594456 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1523510 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.9630. Min Act: -0.0000

Data Index: 811136 (The Pile)

Max Activating Token Index: 768

Text #8

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1654844 (The Pile)

Max Activating Token Index: 733

Text #9

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1087247 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1129299 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.8507. Min Act: -0.0000

Data Index: 902180 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.9017. Min Act: -0.0000

Data Index: 747349 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.8601. Min Act: -0.0000

Data Index: 714193 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1468044 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.8994. Min Act: -0.0000

Data Index: 528367 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1897385 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.8962. Min Act: -0.0000

Data Index: 59183 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.9411. Min Act: -0.0000

Data Index: 894076 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 1.4185. Min Range: -1.4185

Max Act: 0.9071. Min Act: -0.0000

Data Index: 754991 (The Pile)

Max Activating Token Index: 423