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

Dataset: The Pile

Neuron 1600 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.1399. Min Act: -0.0000

Data Index: 1749034 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.8716. Min Act: -0.0000

Data Index: 1301805 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.9119. Min Act: -0.0000

Data Index: 1183124 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.7553. Min Act: -0.0000

Data Index: 1809691 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.1116. Min Act: -0.0000

Data Index: 1737558 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.5428. Min Act: -0.0000

Data Index: 1942582 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.5017. Min Act: -0.0000

Data Index: 573907 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.3778. Min Act: -0.0000

Data Index: 849606 (The Pile)

Max Activating Token Index: 493

Text #8

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.5233. Min Act: -0.0000

Data Index: 470554 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.5437. Min Act: -0.0000

Data Index: 1688672 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.5365. Min Act: -0.0000

Data Index: 680770 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.5829. Min Act: -0.0000

Data Index: 1800376 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.5880. Min Act: -0.0000

Data Index: 21169 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.4539. Min Act: -0.0000

Data Index: 1536140 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.4562. Min Act: -0.0000

Data Index: 1974717 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.4562. Min Act: -0.0000

Data Index: 896528 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.5667. Min Act: -0.0000

Data Index: 547385 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.6851. Min Act: -0.0000

Data Index: 460827 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.7003. Min Act: -0.0000

Data Index: 1708369 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.1453. Min Act: -0.0000

Data Index: 1995574 (The Pile)

Max Activating Token Index: 1016