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

Dataset: The Pile

Neuron 52 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.9286. Min Act: -0.0000

Data Index: 429700 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1931864 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8641. Min Act: -0.0000

Data Index: 519030 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1981266 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1263216 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.9008. Min Act: -0.0000

Data Index: 499329 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8830. Min Act: -0.0000

Data Index: 461246 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8525. Min Act: -0.0000

Data Index: 704778 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1157743 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8456. Min Act: -0.0000

Data Index: 588300 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8760. Min Act: -0.0000

Data Index: 736902 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1806343 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1715839 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8427. Min Act: -0.0000

Data Index: 912606 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1899488 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8554. Min Act: -0.0000

Data Index: 515175 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1623629 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1205397 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.7442. Min Act: -0.0000

Data Index: 125146 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 0.9529. Min Range: -0.9529

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1914659 (The Pile)

Max Activating Token Index: 587