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

Dataset: The Pile

Neuron 3338 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.9019. Min Act: -0.0000

Data Index: 513531 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.4815. Min Act: -0.0000

Data Index: 150567 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.5041. Min Act: -0.0000

Data Index: 1597144 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.5787. Min Act: -0.0000

Data Index: 1159577 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1288257 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2891. Min Act: -0.0000

Data Index: 1808225 (The Pile)

Max Activating Token Index: 120

Text #6

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1729445 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.3609. Min Act: -0.0000

Data Index: 554539 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2514. Min Act: -0.0000

Data Index: 397069 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2733. Min Act: -0.0000

Data Index: 729476 (The Pile)

Max Activating Token Index: 67

Text #10

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.3115. Min Act: -0.0000

Data Index: 1151404 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2993. Min Act: -0.0000

Data Index: 83903 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2455. Min Act: -0.0000

Data Index: 129202 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1696314 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2097. Min Act: -0.0000

Data Index: 512295 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.1921. Min Act: -0.0000

Data Index: 132387 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.2688. Min Act: -0.0000

Data Index: 141238 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.1817. Min Act: -0.0000

Data Index: 730265 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.1778. Min Act: -0.0000

Data Index: 484446 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1534212 (The Pile)

Max Activating Token Index: 663