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

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

Neuron 4432 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4237. Min Range: -2.4237

Max Act: 2.4237. Min Act: -0.0000

Data Index: 1318708 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.7849. Min Act: -0.0000

Data Index: 622396 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.7092. Min Act: -0.0000

Data Index: 721974 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.6089. Min Act: -0.0000

Data Index: 225818 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.7922. Min Act: -0.0000

Data Index: 420674 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.6029. Min Act: -0.0000

Data Index: 873686 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1209580 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.5603. Min Act: -0.0000

Data Index: 906594 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.4544. Min Act: -0.0000

Data Index: 560538 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.5259. Min Act: -0.0000

Data Index: 1114800 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.6214. Min Act: -0.0000

Data Index: 897182 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.5110. Min Act: -0.0000

Data Index: 382518 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.5034. Min Act: -0.0000

Data Index: 25772 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.4962. Min Act: -0.0000

Data Index: 17828 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.4769. Min Act: -0.0000

Data Index: 659373 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.4526. Min Act: -0.0000

Data Index: 528189 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.4609. Min Act: -0.0000

Data Index: 970784 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.4573. Min Act: -0.0000

Data Index: 624646 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1054547 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 2.4237. Min Range: -2.4237

Max Act: 1.4252. Min Act: -0.0000

Data Index: 331058 (C4 (Web Text))

Max Activating Token Index: 227