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

Dataset: The Pile

Neuron 795 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.4663. Min Act: -0.0000

Data Index: 783336 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0429. Min Act: -0.0000

Data Index: 568644 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0924. Min Act: -0.0000

Data Index: 793289 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.9447. Min Act: -0.0000

Data Index: 992055 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.9843. Min Act: -0.0000

Data Index: 431531 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.9758. Min Act: -0.0000

Data Index: 239088 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8681. Min Act: -0.0000

Data Index: 764750 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8587. Min Act: -0.0000

Data Index: 558632 (The Pile)

Max Activating Token Index: 39

Text #8

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8471. Min Act: -0.0000

Data Index: 884605 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1595029 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1698084 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1375556 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8842. Min Act: -0.0000

Data Index: 871978 (The Pile)

Max Activating Token Index: 921

Text #13

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1893347 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1795666 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1149937 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1173198 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1369366 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1641467 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1983828 (The Pile)

Max Activating Token Index: 837