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

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

Neuron 2146 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.1508. Min Act: -0.0000

Data Index: 531866 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0922. Min Act: -0.0000

Data Index: 635915 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0911. Min Act: -0.0000

Data Index: 326614 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0862. Min Act: -0.0000

Data Index: 334352 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0904. Min Act: -0.0000

Data Index: 465628 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0870. Min Act: -0.0000

Data Index: 2069 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0893. Min Act: -0.0000

Data Index: 182098 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0828. Min Act: -0.0000

Data Index: 934314 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1153257 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0784. Min Act: -0.0000

Data Index: 667960 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1096837 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0763. Min Act: -0.0000

Data Index: 833247 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0760. Min Act: -0.0000

Data Index: 849630 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1168616 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0752. Min Act: -0.0000

Data Index: 493157 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0801. Min Act: -0.0000

Data Index: 200021 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0765. Min Act: -0.0000

Data Index: 175450 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1220249 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0776. Min Act: -0.0000

Data Index: 695300 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.1508. Min Range: -0.1508

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1054120 (C4 (Web Text))

Max Activating Token Index: 873