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

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

Neuron 2696 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.8594. Min Act: -0.0000

Data Index: 484769 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.7458. Min Act: -0.0000

Data Index: 1163890 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 3.0370. Min Range: -3.0370

Max Act: 3.0252. Min Act: -0.0000

Data Index: 742592 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 3.0370. Min Range: -3.0370

Max Act: 3.0370. Min Act: -0.0000

Data Index: 242703 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.9085. Min Act: -0.0000

Data Index: 503613 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.6603. Min Act: -0.0000

Data Index: 919183 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.5989. Min Act: -0.0000

Data Index: 207560 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.3439. Min Act: -0.0000

Data Index: 284905 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.4834. Min Act: -0.0000

Data Index: 717495 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.5735. Min Act: -0.0000

Data Index: 1137059 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.5293. Min Act: -0.0000

Data Index: 795659 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.4252. Min Act: -0.0000

Data Index: 1014908 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.5398. Min Act: -0.0000

Data Index: 890319 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.4003. Min Act: -0.0000

Data Index: 1292300 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.4226. Min Act: -0.0000

Data Index: 870948 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.5355. Min Act: -0.0000

Data Index: 744106 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.3826. Min Act: -0.0000

Data Index: 1349932 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.3773. Min Act: -0.0000

Data Index: 553636 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.4949. Min Act: -0.0000

Data Index: 569880 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.6450. Min Act: -0.0000

Data Index: 1009716 (C4 (Web Text))

Max Activating Token Index: 68