Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2267 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1233. Min Act: -0.0003

Data Index: 542534 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1276496 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1033. Min Act: -0.0003

Data Index: 881554 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0971. Min Act: -0.0003

Data Index: 26537 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0992. Min Act: -0.0003

Data Index: 997890 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0841. Min Act: -0.0003

Data Index: 54916 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0853. Min Act: -0.0003

Data Index: 595688 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1252407 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0874. Min Act: -0.0003

Data Index: 342132 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0839. Min Act: -0.0003

Data Index: 344670 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0806. Min Act: -0.0003

Data Index: 398773 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1126557 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0842. Min Act: -0.0003

Data Index: 192414 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0774. Min Act: -0.0003

Data Index: 1180633 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1092892 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0772. Min Act: -0.0003

Data Index: 453500 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0664. Min Act: -0.0003

Data Index: 7318 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0840. Min Act: -0.0003

Data Index: 991901 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0800. Min Act: -0.0003

Data Index: 841285 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0768. Min Act: -0.0003

Data Index: 145462 (C4 (Web Text))

Max Activating Token Index: 56