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

Dataset: The Pile

Neuron 4401 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.2184. Min Act: -0.0000

Data Index: 859424 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1265548 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1596. Min Act: -0.0000

Data Index: 1446651 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1166. Min Act: -0.0000

Data Index: 595905 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0607. Min Act: -0.0000

Data Index: 626747 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1315190 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9864. Min Act: -0.0000

Data Index: 516665 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9700. Min Act: -0.0000

Data Index: 812191 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0173. Min Act: -0.0000

Data Index: 665042 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9822. Min Act: -0.0000

Data Index: 210683 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1333710 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1118314 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0049. Min Act: -0.0000

Data Index: 544200 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1674939 (The Pile)

Max Activating Token Index: 535

Text #14

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1004382 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0023. Min Act: -0.0000

Data Index: 539448 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9320. Min Act: -0.0000

Data Index: 161665 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9832. Min Act: -0.0000

Data Index: 102474 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8700. Min Act: -0.0000

Data Index: 136519 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8634. Min Act: -0.0000

Data Index: 288585 (The Pile)

Max Activating Token Index: 974