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

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

Neuron 5053 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: 0.8551. Min Range: -0.8551

Max Act: 0.8551. Min Act: -0.0000

Data Index: 415494 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6911. Min Act: -0.0000

Data Index: 732996 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6696. Min Act: -0.0000

Data Index: 809864 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6196. Min Act: -0.0000

Data Index: 724334 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5726. Min Act: -0.0000

Data Index: 184075 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5442. Min Act: -0.0000

Data Index: 914130 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5658. Min Act: -0.0000

Data Index: 456650 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5673. Min Act: -0.0000

Data Index: 530421 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4394. Min Act: -0.0000

Data Index: 55613 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4946. Min Act: -0.0000

Data Index: 471459 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1064295 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4631. Min Act: -0.0000

Data Index: 858426 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4508. Min Act: -0.0000

Data Index: 500405 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1237582 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4216. Min Act: -0.0000

Data Index: 722212 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4344. Min Act: -0.0000

Data Index: 789137 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1226857 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4130. Min Act: -0.0000

Data Index: 672112 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.3952. Min Act: -0.0000

Data Index: 141681 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4030. Min Act: -0.0000

Data Index: 220481 (C4 (Web Text))

Max Activating Token Index: 457