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

Dataset: The Pile

Neuron 5101 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: 0.6267. Min Range: -0.6267

Max Act: 0.6221. Min Act: -0.0000

Data Index: 127943 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1665186 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1365169 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6267. Min Act: -0.0000

Data Index: 456915 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1823937 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1272680 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1447301 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5764. Min Act: -0.0000

Data Index: 824498 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1918370 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5503. Min Act: -0.0000

Data Index: 356498 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5678. Min Act: -0.0000

Data Index: 730111 (The Pile)

Max Activating Token Index: 540

Text #11

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5607. Min Act: 0.0000

Data Index: 698594 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1104340 (The Pile)

Max Activating Token Index: 197

Text #13

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5542. Min Act: -0.0000

Data Index: 246871 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1279883 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1174899 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5553. Min Act: -0.0000

Data Index: 153691 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5728. Min Act: -0.0000

Data Index: 499966 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5525. Min Act: -0.0000

Data Index: 374672 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5218. Min Act: -0.0000

Data Index: 241863 (The Pile)

Max Activating Token Index: 768