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

Dataset: The Pile

Neuron 1060 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1197575 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6657. Min Act: -0.0000

Data Index: 846371 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6515. Min Act: -0.0000

Data Index: 737572 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1836246 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6325. Min Act: -0.0000

Data Index: 328412 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1724444 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1249495 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6274. Min Act: -0.0000

Data Index: 400277 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5005. Min Act: -0.0000

Data Index: 406777 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1378843 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6182. Min Act: -0.0000

Data Index: 685356 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1229831 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5531. Min Act: -0.0000

Data Index: 950251 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5555. Min Act: -0.0000

Data Index: 714123 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1199299 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5897. Min Act: -0.0000

Data Index: 259310 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1831326 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1576607 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1605819 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5398. Min Act: -0.0000

Data Index: 975562 (The Pile)

Max Activating Token Index: 484