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

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

Neuron 1256 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8576. Min Act: -0.0001

Data Index: 651709 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8737. Min Act: -0.0001

Data Index: 1192910 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7502. Min Act: -0.0001

Data Index: 627293 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8664. Min Act: -0.0001

Data Index: 1052182 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7779. Min Act: -0.0001

Data Index: 1283616 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7259. Min Act: -0.0001

Data Index: 1180529 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7204. Min Act: -0.0001

Data Index: 17825 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7108. Min Act: -0.0001

Data Index: 1136124 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6895. Min Act: -0.0001

Data Index: 602729 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6254. Min Act: -0.0001

Data Index: 1270611 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6653. Min Act: -0.0001

Data Index: 561289 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7163. Min Act: -0.0001

Data Index: 825190 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7386. Min Act: -0.0001

Data Index: 329215 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6793. Min Act: -0.0001

Data Index: 870520 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6307. Min Act: -0.0001

Data Index: 363359 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5889. Min Act: -0.0001

Data Index: 594207 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5936. Min Act: -0.0001

Data Index: 897344 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6624. Min Act: -0.0001

Data Index: 520770 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6551. Min Act: -0.0001

Data Index: 1043216 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5703. Min Act: -0.0001

Data Index: 580074 (C4 (Web Text))

Max Activating Token Index: 627