Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5863 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.2917. Min Range: -8.2917

Max Act: 8.2917. Min Act: -0.0000

Data Index: 1184546 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 8.2917. Min Range: -8.2917

Max Act: 7.6008. Min Act: -0.0001

Data Index: 619008 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.6747. Min Act: -0.0001

Data Index: 103413 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.7777. Min Act: -0.0001

Data Index: 574427 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.7358. Min Act: -0.0001

Data Index: 24059 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.9072. Min Act: -0.0001

Data Index: 1261489 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.5447. Min Act: -0.0000

Data Index: 866293 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.6973. Min Act: -0.0000

Data Index: 854386 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.0528. Min Act: -0.0001

Data Index: 640181 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.8071. Min Act: -0.0001

Data Index: 793470 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.9614. Min Act: -0.0001

Data Index: 397620 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.0610. Min Act: -0.0001

Data Index: 436544 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 8.2917. Min Range: -8.2917

Max Act: 6.0316. Min Act: -0.0000

Data Index: 30941 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.6510. Min Act: -0.0001

Data Index: 219750 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.9771. Min Act: -0.0000

Data Index: 950786 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.4329. Min Act: -0.0001

Data Index: 566019 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.9068. Min Act: -0.0000

Data Index: 1336937 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.4886. Min Act: -0.0000

Data Index: 562009 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.4098. Min Act: -0.0001

Data Index: 756015 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 8.2917. Min Range: -8.2917

Max Act: 5.3389. Min Act: -0.0000

Data Index: 798565 (C4 (Web Text))

Max Activating Token Index: 75