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

Dataset: The Pile

Neuron 1551 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: 5.5149. Min Range: -5.5149

Max Act: 5.5149. Min Act: -0.0000

Data Index: 10433 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.4855. Min Act: -0.0000

Data Index: 841197 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.4375. Min Act: -0.0000

Data Index: 1686410 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 5.5149. Min Range: -5.5149

Max Act: 3.9714. Min Act: -0.0000

Data Index: 843505 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.4573. Min Act: -0.0000

Data Index: 1497814 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 5.5149. Min Range: -5.5149

Max Act: 3.8691. Min Act: -0.0000

Data Index: 1811348 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.2287. Min Act: -0.0000

Data Index: 1274858 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.2365. Min Act: -0.0000

Data Index: 632127 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.2976. Min Act: -0.0000

Data Index: 55965 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 5.5149. Min Range: -5.5149

Max Act: 3.9946. Min Act: -0.0000

Data Index: 1574658 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.3250. Min Act: 0.0000

Data Index: 1128866 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.3347. Min Act: -0.0000

Data Index: 1790458 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.2529. Min Act: -0.0000

Data Index: 1552366 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.4561. Min Act: 0.0000

Data Index: 1029272 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.2040. Min Act: -0.0000

Data Index: 73588 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 5.5149. Min Range: -5.5149

Max Act: 3.7931. Min Act: -0.0000

Data Index: 1786702 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 5.5149. Min Range: -5.5149

Max Act: 4.1120. Min Act: -0.0000

Data Index: 1360637 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 5.5149. Min Range: -5.5149

Max Act: 3.8715. Min Act: 0.0000

Data Index: 1129877 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 5.5149. Min Range: -5.5149

Max Act: 3.9996. Min Act: -0.0000

Data Index: 1567285 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 5.5149. Min Range: -5.5149

Max Act: 3.8001. Min Act: -0.0000

Data Index: 1997438 (The Pile)

Max Activating Token Index: 222