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

Dataset: The Pile

Neuron 3454 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: 1.5113. Min Range: -1.5113

Max Act: 1.4280. Min Act: -0.0000

Data Index: 200348 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.5113. Min Act: -0.0000

Data Index: 1352891 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.3812. Min Act: -0.0000

Data Index: 268373 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1224325 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1885061 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.2608. Min Act: -0.0000

Data Index: 93599 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.1934. Min Act: -0.0000

Data Index: 815895 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.2119. Min Act: -0.0000

Data Index: 921422 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1857619 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1285612 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1883796 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1857375 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1649060 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1747949 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1043310 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1643344 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1159388 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1836823 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9370. Min Act: -0.0000

Data Index: 590914 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1470892 (The Pile)

Max Activating Token Index: 72