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

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

Neuron 25 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: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0001

Data Index: 533930 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1027. Min Act: -0.0001

Data Index: 373104 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1122998 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1177070 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0980. Min Act: -0.0001

Data Index: 225869 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0957. Min Act: -0.0001

Data Index: 888984 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0874. Min Act: -0.0001

Data Index: 826565 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1224575 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1203424 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1057399 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0898. Min Act: -0.0001

Data Index: 627044 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0894. Min Act: -0.0001

Data Index: 657991 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1232287 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0885. Min Act: -0.0001

Data Index: 790518 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1060400 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1035272 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1153323 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0820. Min Act: -0.0001

Data Index: 19641 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1315314 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1341002 (C4 (Web Text))

Max Activating Token Index: 763