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

Dataset: The Pile

Neuron 3695 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: 1.4358. Min Range: -1.4358

Max Act: 1.3749. Min Act: -0.0000

Data Index: 759475 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.4358. Min Act: -0.0000

Data Index: 513439 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1757. Min Act: -0.0000

Data Index: 752985 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1867. Min Act: -0.0000

Data Index: 878868 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1729. Min Act: -0.0000

Data Index: 543640 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1736. Min Act: -0.0000

Data Index: 1474352 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1582391 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1860213 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1110. Min Act: -0.0000

Data Index: 789915 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0927. Min Act: -0.0000

Data Index: 499771 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1974656 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0560. Min Act: -0.0000

Data Index: 949598 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0565. Min Act: -0.0000

Data Index: 969836 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1416150 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0519. Min Act: -0.0000

Data Index: 359184 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1287636 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1921518 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1589440 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1890455 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0457. Min Act: -0.0000

Data Index: 731114 (The Pile)

Max Activating Token Index: 16