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

Dataset: The Pile

Neuron 2734 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8894. Min Act: -0.0000

Data Index: 724560 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8513. Min Act: -0.0000

Data Index: 805748 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7572. Min Act: -0.0000

Data Index: 498960 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1242122 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8201. Min Act: -0.0000

Data Index: 192286 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1074444 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1823904 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1176983 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1168896 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7516. Min Act: -0.0000

Data Index: 192631 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1897411 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1198191 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1528390 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1736013 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1347769 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6605. Min Act: -0.0000

Data Index: 892520 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1505533 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8894. Min Act: -0.0000

Data Index: 935617 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6434. Min Act: -0.0000

Data Index: 87736 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7042. Min Act: -0.0000

Data Index: 788660 (The Pile)

Max Activating Token Index: 852