Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5903 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3836. Min Range: -4.3836

Max Act: 4.3836. Min Act: -0.0000

Data Index: 1315588 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 4.3836. Min Range: -4.3836

Max Act: 4.1676. Min Act: -0.0001

Data Index: 1049059 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.6149. Min Act: -0.0000

Data Index: 636336 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.8018. Min Act: -0.0001

Data Index: 1213157 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.6226. Min Act: -0.0000

Data Index: 262918 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.6114. Min Act: -0.0000

Data Index: 343256 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.7523. Min Act: -0.0000

Data Index: 641914 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.9203. Min Act: -0.0001

Data Index: 152239 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.5611. Min Act: -0.0000

Data Index: 690346 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.5001. Min Act: -0.0000

Data Index: 621703 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.4604. Min Act: -0.0001

Data Index: 468193 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.4626. Min Act: -0.0000

Data Index: 566406 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.7756. Min Act: -0.0000

Data Index: 1009559 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.4498. Min Act: -0.0000

Data Index: 980175 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.3087. Min Act: -0.0000

Data Index: 1062492 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.4332. Min Act: -0.0001

Data Index: 806082 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.2570. Min Act: -0.0000

Data Index: 1134621 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.2906. Min Act: -0.0000

Data Index: 450861 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.3904. Min Act: -0.0001

Data Index: 1103225 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 4.3836. Min Range: -4.3836

Max Act: 3.3458. Min Act: -0.0001

Data Index: 1318557 (C4 (Web Text))

Max Activating Token Index: 145