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

Dataset: The Pile

Neuron 4004 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: 0.4098. Min Range: -0.4098

Max Act: 0.3860. Min Act: -0.0000

Data Index: 311611 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.4098. Min Act: -0.0001

Data Index: 572647 (The Pile)

Max Activating Token Index: 594

Text #2

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3055. Min Act: -0.0000

Data Index: 170330 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1164029 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3178. Min Act: -0.0000

Data Index: 143513 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3300. Min Act: -0.0000

Data Index: 972193 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1865205 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2745. Min Act: -0.0000

Data Index: 620843 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3015. Min Act: -0.0000

Data Index: 824145 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1773963 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2646. Min Act: -0.0000

Data Index: 211396 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2846. Min Act: -0.0000

Data Index: 293811 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2809. Min Act: -0.0000

Data Index: 585731 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1276630 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1426776 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1560535 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2641. Min Act: -0.0000

Data Index: 255437 (The Pile)

Max Activating Token Index: 165

Text #17

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1588087 (The Pile)

Max Activating Token Index: 866

Text #18

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1857009 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2669. Min Act: -0.0000

Data Index: 986017 (The Pile)

Max Activating Token Index: 913