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

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

Neuron 4216 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.7845. Min Act: -0.0001

Data Index: 73610 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.7137. Min Act: -0.0001

Data Index: 133694 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.7041. Min Act: -0.0001

Data Index: 1184309 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.6503. Min Act: -0.0000

Data Index: 1128909 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.5912. Min Act: -0.0001

Data Index: 1145936 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.4838. Min Act: -0.0001

Data Index: 1193844 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.4513. Min Act: -0.0001

Data Index: 425250 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.5317. Min Act: -0.0001

Data Index: 690679 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.5673. Min Act: -0.0001

Data Index: 503877 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.6569. Min Act: -0.0001

Data Index: 307809 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.5338. Min Act: -0.0001

Data Index: 1171717 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.3658. Min Act: -0.0001

Data Index: 1397251 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.4652. Min Act: -0.0001

Data Index: 34008 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.4164. Min Act: -0.0001

Data Index: 1199555 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.2610. Min Act: -0.0001

Data Index: 96587 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.4548. Min Act: -0.0001

Data Index: 92848 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.3762. Min Act: -0.0001

Data Index: 778072 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.3202. Min Act: -0.0000

Data Index: 115918 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.4170. Min Act: -0.0001

Data Index: 1333302 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.7845. Min Range: -1.7845

Max Act: 1.3433. Min Act: -0.0001

Data Index: 164023 (C4 (Web Text))

Max Activating Token Index: 142