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

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

Neuron 2846 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.3829. Min Act: -0.0000

Data Index: 311921 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.3213. Min Act: -0.0000

Data Index: 865587 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.3248. Min Act: -0.0000

Data Index: 76209 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.3098. Min Act: -0.0000

Data Index: 703228 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2915. Min Act: -0.0000

Data Index: 39452 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.3090. Min Act: -0.0000

Data Index: 601395 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.3079. Min Act: -0.0000

Data Index: 798685 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1328980 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2806. Min Act: -0.0000

Data Index: 965982 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2723. Min Act: -0.0000

Data Index: 510618 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2662. Min Act: -0.0000

Data Index: 870770 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2729. Min Act: -0.0000

Data Index: 808486 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2705. Min Act: -0.0000

Data Index: 136445 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2719. Min Act: -0.0000

Data Index: 945969 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2578. Min Act: -0.0000

Data Index: 549266 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2652. Min Act: -0.0000

Data Index: 340633 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2561. Min Act: -0.0000

Data Index: 70378 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2724. Min Act: -0.0000

Data Index: 671308 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2580. Min Act: -0.0000

Data Index: 31039 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.3829. Min Range: -0.3829

Max Act: 0.2576. Min Act: -0.0000

Data Index: 278990 (C4 (Web Text))

Max Activating Token Index: 529