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

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

Neuron 2015 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: 1.4903. Min Range: -1.4903

Max Act: 1.4903. Min Act: -0.0000

Data Index: 835298 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.3487. Min Act: -0.0000

Data Index: 167369 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1269725 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1103. Min Act: -0.0000

Data Index: 237207 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1037. Min Act: -0.0000

Data Index: 393704 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1672. Min Act: -0.0000

Data Index: 173286 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1195. Min Act: -0.0000

Data Index: 792405 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1630. Min Act: -0.0000

Data Index: 346541 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1883. Min Act: -0.0000

Data Index: 464477 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0792. Min Act: -0.0000

Data Index: 388268 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1266463 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0354. Min Act: -0.0000

Data Index: 923478 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0645. Min Act: -0.0000

Data Index: 861443 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1158130 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0387. Min Act: -0.0000

Data Index: 593671 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0350. Min Act: -0.0000

Data Index: 578789 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0384. Min Act: -0.0000

Data Index: 307910 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0238. Min Act: -0.0000

Data Index: 914984 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9941. Min Act: -0.0000

Data Index: 579117 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1085343 (C4 (Web Text))

Max Activating Token Index: 611