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

Dataset: The Pile

Neuron 2416 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: 1.5393. Min Range: -1.5393

Max Act: 1.5393. Min Act: -0.0000

Data Index: 1528141 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3312. Min Act: -0.0000

Data Index: 30937 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3570. Min Act: -0.0000

Data Index: 479383 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1439433 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3378. Min Act: -0.0000

Data Index: 960926 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1793. Min Act: -0.0000

Data Index: 293045 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3329. Min Act: -0.0000

Data Index: 1500054 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1195380 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3726. Min Act: -0.0000

Data Index: 1626479 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1036539 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2312. Min Act: -0.0000

Data Index: 31683 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1846556 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1358032 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2670. Min Act: -0.0000

Data Index: 18933 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2659. Min Act: -0.0000

Data Index: 489266 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1651231 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2408. Min Act: -0.0000

Data Index: 1024465 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1872. Min Act: -0.0000

Data Index: 987055 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2608. Min Act: -0.0000

Data Index: 95472 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1067. Min Act: -0.0000

Data Index: 97249 (The Pile)

Max Activating Token Index: 978