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

Dataset: The Pile

Neuron 723 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: 0.7638. Min Range: -0.7638

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1449686 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1846956 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1687916 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1937057 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6162. Min Act: -0.0000

Data Index: 205723 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1235991 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1291630 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5375. Min Act: -0.0000

Data Index: 405394 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5298. Min Act: -0.0000

Data Index: 935767 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6043. Min Act: -0.0000

Data Index: 736296 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1857101 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1458947 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1238612 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1539091 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.4908. Min Act: -0.0000

Data Index: 201046 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1422735 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5290. Min Act: -0.0000

Data Index: 187330 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1249047 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1305130 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5212. Min Act: -0.0000

Data Index: 877268 (The Pile)

Max Activating Token Index: 725