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

Dataset: The Pile

Neuron 1210 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3737. Min Range: -2.3737

Max Act: 2.3737. Min Act: -0.0000

Data Index: 1497336 (The Pile)

Max Activating Token Index: 639

Text #1

Max Range: 2.3737. Min Range: -2.3737

Max Act: 2.1462. Min Act: -0.0000

Data Index: 883552 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.8970. Min Act: -0.0000

Data Index: 1077925 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6522. Min Act: -0.0000

Data Index: 1966431 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6269. Min Act: -0.0000

Data Index: 342824 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 2.3737. Min Range: -2.3737

Max Act: 2.0028. Min Act: -0.0000

Data Index: 1827720 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.7100. Min Act: -0.0000

Data Index: 907780 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.7326. Min Act: -0.0000

Data Index: 794029 (The Pile)

Max Activating Token Index: 746

Text #8

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6162. Min Act: -0.0000

Data Index: 178910 (The Pile)

Max Activating Token Index: 850

Text #9

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6551. Min Act: -0.0000

Data Index: 233001 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6536. Min Act: -0.0000

Data Index: 185604 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6485. Min Act: -0.0000

Data Index: 744878 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.5943. Min Act: -0.0000

Data Index: 1035312 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6385. Min Act: -0.0000

Data Index: 678194 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6304. Min Act: -0.0000

Data Index: 513666 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.4845. Min Act: -0.0000

Data Index: 635075 (The Pile)

Max Activating Token Index: 303

Text #16

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6422. Min Act: -0.0000

Data Index: 871798 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.5624. Min Act: -0.0000

Data Index: 970579 (The Pile)

Max Activating Token Index: 952

Text #18

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.4479. Min Act: -0.0000

Data Index: 107455 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.5307. Min Act: -0.0000

Data Index: 295820 (The Pile)

Max Activating Token Index: 385