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

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

Neuron 5019 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9923. Min Act: -0.0000

Data Index: 554622 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8676. Min Act: -0.0000

Data Index: 134175 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9407. Min Act: -0.0000

Data Index: 672854 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9213. Min Act: -0.0000

Data Index: 28505 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7848. Min Act: -0.0000

Data Index: 481512 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1345597 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1349029 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1110968 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6984. Min Act: -0.0000

Data Index: 732931 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7399. Min Act: -0.0000

Data Index: 891705 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7230. Min Act: -0.0000

Data Index: 310117 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7004. Min Act: -0.0000

Data Index: 716732 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7157. Min Act: -0.0000

Data Index: 654279 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1244250 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1015601 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1318820 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6594. Min Act: -0.0000

Data Index: 475224 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6385. Min Act: -0.0000

Data Index: 968128 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6383. Min Act: -0.0000

Data Index: 740106 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6162. Min Act: -0.0000

Data Index: 40868 (C4 (Web Text))

Max Activating Token Index: 960