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

Dataset: The Pile

Neuron 2129 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: 1.6966. Min Range: -1.6966

Max Act: 1.6966. Min Act: -0.0000

Data Index: 1690463 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.6756. Min Act: -0.0000

Data Index: 593481 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.5788. Min Act: 0.0000

Data Index: 995005 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.5247. Min Act: -0.0000

Data Index: 995365 (The Pile)

Max Activating Token Index: 802

Text #4

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.4944. Min Act: -0.0000

Data Index: 1067519 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.3287. Min Act: -0.0000

Data Index: 376603 (The Pile)

Max Activating Token Index: 802

Text #6

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.4458. Min Act: 0.0000

Data Index: 424564 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.3720. Min Act: -0.0000

Data Index: 987443 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.3933. Min Act: -0.0000

Data Index: 1213391 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2722. Min Act: 0.0000

Data Index: 1416080 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.3492. Min Act: -0.0000

Data Index: 637520 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2657. Min Act: -0.0000

Data Index: 611956 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2736. Min Act: -0.0000

Data Index: 439934 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.3687. Min Act: -0.0000

Data Index: 956510 (The Pile)

Max Activating Token Index: 446

Text #14

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2833. Min Act: -0.0000

Data Index: 349088 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1450216 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.3081. Min Act: -0.0000

Data Index: 208042 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1852633 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2249. Min Act: -0.0000

Data Index: 527893 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2985. Min Act: -0.0000

Data Index: 885051 (The Pile)

Max Activating Token Index: 761