Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 510 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.4792. Min Act: -0.0001

Data Index: 672363 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.2607. Min Act: -0.0001

Data Index: 76196 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.2458. Min Act: -0.0001

Data Index: 659441 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.1601. Min Act: -0.0001

Data Index: 245467 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.1076. Min Act: -0.0001

Data Index: 518184 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0648. Min Act: -0.0001

Data Index: 939835 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.1115. Min Act: -0.0001

Data Index: 618630 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0907. Min Act: -0.0001

Data Index: 657814 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0522. Min Act: -0.0001

Data Index: 317880 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9763. Min Act: -0.0001

Data Index: 640711 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.8866. Min Act: -0.0001

Data Index: 1174303 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9434. Min Act: -0.0001

Data Index: 588867 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9083. Min Act: -0.0001

Data Index: 43451 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9412. Min Act: -0.0001

Data Index: 719995 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9026. Min Act: -0.0001

Data Index: 1224305 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.8927. Min Act: -0.0001

Data Index: 820169 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9185. Min Act: -0.0001

Data Index: 1201372 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.8944. Min Act: -0.0001

Data Index: 245293 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.8894. Min Act: -0.0001

Data Index: 831185 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9143. Min Act: -0.0001

Data Index: 768587 (C4 (Web Text))

Max Activating Token Index: 358