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

Dataset: The Pile

Neuron 2483 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: 0.8364. Min Range: -0.8364

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1838309 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6123. Min Act: -0.0000

Data Index: 861547 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1026791 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1895443 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1534290 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1597463 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1419905 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5242. Min Act: -0.0000

Data Index: 282881 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1852563 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5015. Min Act: -0.0000

Data Index: 477814 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.4529. Min Act: -0.0000

Data Index: 810414 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5096. Min Act: -0.0000

Data Index: 290270 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5082. Min Act: -0.0000

Data Index: 184201 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1546271 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5061. Min Act: -0.0000

Data Index: 750379 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1825308 (The Pile)

Max Activating Token Index: 684

Text #16

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1163753 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1588017 (The Pile)

Max Activating Token Index: 678

Text #18

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1935721 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5141. Min Act: -0.0000

Data Index: 236975 (The Pile)

Max Activating Token Index: 185