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

Dataset: The Pile

Neuron 3514 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: 1.6851. Min Range: -1.6851

Max Act: 1.6851. Min Act: -0.0000

Data Index: 849417 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.3071. Min Act: -0.0000

Data Index: 530782 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.2372. Min Act: -0.0000

Data Index: 575241 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.1710. Min Act: -0.0000

Data Index: 396330 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.1098. Min Act: -0.0000

Data Index: 469519 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.0154. Min Act: -0.0000

Data Index: 190932 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.0437. Min Act: -0.0000

Data Index: 655239 (The Pile)

Max Activating Token Index: 392

Text #7

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1893682 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1813108 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1908667 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1783660 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1130397 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.9154. Min Act: 0.0000

Data Index: 1626750 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.9564. Min Act: -0.0000

Data Index: 700809 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.8920. Min Act: -0.0000

Data Index: 695764 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.9388. Min Act: -0.0000

Data Index: 969789 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.8917. Min Act: -0.0000

Data Index: 547282 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1423575 (The Pile)

Max Activating Token Index: 239

Text #18

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.8769. Min Act: -0.0000

Data Index: 331822 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 1.6851. Min Range: -1.6851

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1316245 (The Pile)

Max Activating Token Index: 786