Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1818110 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1262298 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1492500 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6416. Min Act: -0.0000

Data Index: 214234 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6317. Min Act: -0.0000

Data Index: 99555 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1603318 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1444385 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4888. Min Act: -0.0000

Data Index: 552549 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4952. Min Act: -0.0000

Data Index: 956629 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1407740 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4693. Min Act: -0.0000

Data Index: 775907 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1561127 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4860. Min Act: 0.0000

Data Index: 334976 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4680. Min Act: -0.0000

Data Index: 397382 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4587. Min Act: 0.0000

Data Index: 792836 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4729. Min Act: -0.0000

Data Index: 235368 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4480. Min Act: -0.0000

Data Index: 860857 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4478. Min Act: -0.0000

Data Index: 896252 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1062771 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4045. Min Act: -0.0000

Data Index: 132344 (The Pile)

Max Activating Token Index: 110