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

Dataset: The Pile

Neuron 3431 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3001. Min Act: -0.0000

Data Index: 1652108 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.4907. Min Act: -0.0000

Data Index: 1953322 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.2762. Min Act: -0.0000

Data Index: 701041 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.1286. Min Act: -0.0000

Data Index: 1766747 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.2714. Min Act: -0.0000

Data Index: 1877472 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3607. Min Act: -0.0000

Data Index: 208697 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.1699. Min Act: -0.0000

Data Index: 1404945 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.0263. Min Act: -0.0000

Data Index: 684490 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3012. Min Act: -0.0000

Data Index: 352505 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.2503. Min Act: -0.0000

Data Index: 1812802 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.0789. Min Act: -0.0000

Data Index: 1771096 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 3.4907. Min Range: -3.4907

Max Act: 2.8805. Min Act: -0.0000

Data Index: 310730 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 3.4907. Min Range: -3.4907

Max Act: 2.8794. Min Act: -0.0000

Data Index: 283053 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 3.4907. Min Range: -3.4907

Max Act: 2.6249. Min Act: -0.0000

Data Index: 945631 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 3.4907. Min Range: -3.4907

Max Act: 2.7232. Min Act: -0.0000

Data Index: 1027588 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 3.4907. Min Range: -3.4907

Max Act: 2.8594. Min Act: -0.0000

Data Index: 1510369 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 3.4907. Min Range: -3.4907

Max Act: 2.9717. Min Act: -0.0000

Data Index: 1935863 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 3.4907. Min Range: -3.4907

Max Act: 2.9554. Min Act: -0.0000

Data Index: 485593 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.1149. Min Act: -0.0000

Data Index: 925442 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 3.4907. Min Range: -3.4907

Max Act: 2.7836. Min Act: -0.0000

Data Index: 75565 (The Pile)

Max Activating Token Index: 151