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

Dataset: The Pile

Neuron 2158 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: 1.7584. Min Range: -1.7584

Max Act: 1.6981. Min Act: -0.0000

Data Index: 1526259 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.7584. Min Act: -0.0000

Data Index: 614014 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.7367. Min Act: -0.0000

Data Index: 413352 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.5455. Min Act: -0.0000

Data Index: 20452 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.5169. Min Act: -0.0000

Data Index: 945276 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.3714. Min Act: -0.0000

Data Index: 229528 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.4434. Min Act: -0.0000

Data Index: 655660 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.4933. Min Act: -0.0000

Data Index: 332880 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.4674. Min Act: -0.0000

Data Index: 176806 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.4637. Min Act: -0.0000

Data Index: 205488 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1631062 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.3604. Min Act: -0.0000

Data Index: 607587 (The Pile)

Max Activating Token Index: 405

Text #12

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.1821. Min Act: -0.0000

Data Index: 655332 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2889. Min Act: -0.0000

Data Index: 1380753 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1401404 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1792726 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1156600 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.0754. Min Act: -0.0000

Data Index: 462870 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.1348. Min Act: -0.0000

Data Index: 98953 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.0631. Min Act: -0.0000

Data Index: 184303 (The Pile)

Max Activating Token Index: 774