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

Dataset: The Pile

Neuron 5035 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: 0.8313. Min Range: -0.8313

Max Act: 0.8313. Min Act: -0.0000

Data Index: 267438 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.7347. Min Act: -0.0000

Data Index: 513135 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1691788 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.7428. Min Act: -0.0000

Data Index: 793509 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1057258 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1453984 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1045960 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5481. Min Act: -0.0000

Data Index: 834857 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1604805 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6633. Min Act: -0.0000

Data Index: 856934 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1341759 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6693. Min Act: -0.0000

Data Index: 817503 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1679589 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6359. Min Act: -0.0000

Data Index: 652586 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6765. Min Act: -0.0000

Data Index: 62742 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1402467 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1320142 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1588963 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1389745 (The Pile)

Max Activating Token Index: 536

Text #19

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6685. Min Act: -0.0000

Data Index: 64119 (The Pile)

Max Activating Token Index: 776