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

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

Neuron 2653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4587. Min Range: -3.4587

Max Act: 3.4587. Min Act: -0.0000

Data Index: 609515 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.9965. Min Act: -0.0000

Data Index: 193185 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.9051. Min Act: -0.0000

Data Index: 1122180 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.5889. Min Act: -0.0000

Data Index: 1023721 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.5528. Min Act: -0.0001

Data Index: 650610 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.7847. Min Act: -0.0000

Data Index: 46305 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.6469. Min Act: -0.0000

Data Index: 941973 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.5785. Min Act: -0.0000

Data Index: 1343894 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.1565. Min Act: -0.0000

Data Index: 842855 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.5111. Min Act: -0.0000

Data Index: 872119 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.4642. Min Act: -0.0000

Data Index: 465864 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.3255. Min Act: -0.0000

Data Index: 1215698 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.3241. Min Act: -0.0000

Data Index: 1282258 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.1653. Min Act: -0.0000

Data Index: 811661 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.3830. Min Act: -0.0000

Data Index: 228768 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 3.4587. Min Range: -3.4587

Max Act: 1.9851. Min Act: -0.0000

Data Index: 1254027 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.1797. Min Act: -0.0000

Data Index: 1537 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.1475. Min Act: -0.0000

Data Index: 529901 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 3.4587. Min Range: -3.4587

Max Act: 2.0222. Min Act: -0.0000

Data Index: 1279564 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 3.4587. Min Range: -3.4587

Max Act: 1.8978. Min Act: -0.0000

Data Index: 559801 (C4 (Web Text))

Max Activating Token Index: 958