Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 526 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.5602. Min Act: -0.0001

Data Index: 424692 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.5611. Min Act: -0.0001

Data Index: 1073543 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.5081. Min Act: -0.0001

Data Index: 253997 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4941. Min Act: -0.0001

Data Index: 594755 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.5029. Min Act: -0.0001

Data Index: 691103 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4463. Min Act: -0.0001

Data Index: 596576 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4661. Min Act: -0.0001

Data Index: 85880 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4700. Min Act: -0.0001

Data Index: 1191326 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4610. Min Act: -0.0001

Data Index: 881234 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1309904 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4810. Min Act: -0.0001

Data Index: 884545 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4654. Min Act: -0.0001

Data Index: 876871 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4669. Min Act: -0.0001

Data Index: 1256856 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4789. Min Act: -0.0001

Data Index: 1138311 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4476. Min Act: -0.0001

Data Index: 1151021 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4357. Min Act: -0.0001

Data Index: 170869 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4179. Min Act: -0.0001

Data Index: 890479 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4166. Min Act: -0.0001

Data Index: 1356106 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4068. Min Act: -0.0001

Data Index: 478725 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.5611. Min Range: -0.5611

Max Act: 0.4359. Min Act: -0.0001

Data Index: 415267 (C4 (Web Text))

Max Activating Token Index: 365