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

Dataset: The Pile

Neuron 3023 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: 0.7247. Min Range: -0.7247

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1587375 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1288802 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5854. Min Act: -0.0000

Data Index: 575123 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1797337 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1143627 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1151419 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4341. Min Act: -0.0000

Data Index: 32753 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1204288 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1819813 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1399840 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4044. Min Act: -0.0000

Data Index: 440070 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4314. Min Act: -0.0000

Data Index: 628384 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4126. Min Act: -0.0000

Data Index: 164721 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1099555 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1472580 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1718803 (The Pile)

Max Activating Token Index: 244

Text #16

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1065771 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.3589. Min Act: -0.0000

Data Index: 407544 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.3667. Min Act: -0.0000

Data Index: 406707 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1515715 (The Pile)

Max Activating Token Index: 1002