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

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

Neuron 4619 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1744. Min Range: -3.1744

Max Act: 3.1744. Min Act: -0.0000

Data Index: 1332400 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.8880. Min Act: -0.0000

Data Index: 189647 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.7292. Min Act: -0.0000

Data Index: 113489 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.7062. Min Act: -0.0000

Data Index: 788055 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.6817. Min Act: -0.0000

Data Index: 976161 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.6358. Min Act: -0.0000

Data Index: 41345 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.5629. Min Act: -0.0000

Data Index: 710921 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.5388. Min Act: -0.0000

Data Index: 1207440 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.5339. Min Act: -0.0000

Data Index: 265300 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.5023. Min Act: -0.0000

Data Index: 46832 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.5061. Min Act: -0.0000

Data Index: 295759 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.4881. Min Act: -0.0000

Data Index: 1144710 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.3564. Min Act: -0.0000

Data Index: 694418 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1027388 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.3702. Min Act: -0.0000

Data Index: 307041 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.1158. Min Act: -0.0000

Data Index: 92000 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.3040. Min Act: -0.0000

Data Index: 1100654 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.2816. Min Act: -0.0000

Data Index: 1435670 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.2698. Min Act: -0.0000

Data Index: 782668 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 3.1744. Min Range: -3.1744

Max Act: 2.2582. Min Act: -0.0000

Data Index: 796419 (C4 (Web Text))

Max Activating Token Index: 29