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

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

Neuron 4491 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1725. Min Act: -0.0001

Data Index: 508531 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1335. Min Act: -0.0001

Data Index: 672117 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1067619 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1454331 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1076. Min Act: -0.0001

Data Index: 677455 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1092. Min Act: -0.0001

Data Index: 627242 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1076. Min Act: -0.0001

Data Index: 34668 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1073479 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1329515 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1474678 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0930. Min Act: -0.0001

Data Index: 141076 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0834. Min Act: -0.0001

Data Index: 203428 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1321383 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0756. Min Act: -0.0001

Data Index: 849951 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0884. Min Act: -0.0001

Data Index: 807761 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0853. Min Act: -0.0001

Data Index: 272818 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0874. Min Act: -0.0001

Data Index: 938033 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0848. Min Act: -0.0001

Data Index: 836783 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0871. Min Act: -0.0001

Data Index: 341000 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.0939. Min Act: -0.0001

Data Index: 850243 (C4 (Web Text))

Max Activating Token Index: 74