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

Dataset: The Pile

Neuron 3977 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1003233 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1800041 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1650. Min Act: -0.0000

Data Index: 598097 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1706. Min Act: -0.0000

Data Index: 861611 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1734. Min Act: -0.0000

Data Index: 40682 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1718. Min Act: -0.0000

Data Index: 275952 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1668983 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1800900 (The Pile)

Max Activating Token Index: 658

Text #8

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1032421 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1537. Min Act: -0.0000

Data Index: 937744 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1441116 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1668. Min Act: -0.0000

Data Index: 782086 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1061279 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1836200 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1581. Min Act: -0.0000

Data Index: 721586 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1476. Min Act: -0.0000

Data Index: 327106 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1424. Min Act: -0.0000

Data Index: 368758 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1859749 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1499. Min Act: -0.0000

Data Index: 790179 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1457. Min Act: -0.0000

Data Index: 684942 (The Pile)

Max Activating Token Index: 339