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

Dataset: The Pile

Neuron 1506 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: 1.3534. Min Range: -1.3534

Max Act: 1.1219. Min Act: -0.0000

Data Index: 399691 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.3534. Min Act: -0.0000

Data Index: 780094 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1734847 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1802716 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1826861 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1878848 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1712999 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9444. Min Act: -0.0000

Data Index: 499722 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1487881 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1396805 (The Pile)

Max Activating Token Index: 67

Text #10

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1005993 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1824526 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1637880 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.8414. Min Act: -0.0000

Data Index: 715631 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1600169 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1253937 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.8794. Min Act: -0.0000

Data Index: 91189 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1910812 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1935912 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.8855. Min Act: -0.0000

Data Index: 376572 (The Pile)

Max Activating Token Index: 247