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

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

Neuron 916 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: 4.2806. Min Range: -4.2806

Max Act: 4.2806. Min Act: -0.0000

Data Index: 1073554 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 4.2806. Min Range: -4.2806

Max Act: 3.7589. Min Act: -0.0000

Data Index: 57599 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 4.2806. Min Range: -4.2806

Max Act: 3.5439. Min Act: -0.0000

Data Index: 211607 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 4.2806. Min Range: -4.2806

Max Act: 3.1847. Min Act: -0.0000

Data Index: 376795 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 4.2806. Min Range: -4.2806

Max Act: 3.1835. Min Act: -0.0000

Data Index: 1352645 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 4.2806. Min Range: -4.2806

Max Act: 3.1254. Min Act: -0.0000

Data Index: 988775 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.9724. Min Act: -0.0000

Data Index: 232083 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.9015. Min Act: -0.0000

Data Index: 1163818 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.8691. Min Act: -0.0000

Data Index: 784769 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.6549. Min Act: -0.0000

Data Index: 951916 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.9112. Min Act: -0.0000

Data Index: 620244 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.6479. Min Act: -0.0000

Data Index: 471234 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.5973. Min Act: -0.0000

Data Index: 322988 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.5222. Min Act: -0.0000

Data Index: 63189 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.3675. Min Act: -0.0000

Data Index: 930757 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.5795. Min Act: -0.0000

Data Index: 1111437 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.7074. Min Act: -0.0000

Data Index: 1120068 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.4362. Min Act: -0.0000

Data Index: 1253214 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.2784. Min Act: -0.0000

Data Index: 1069487 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 4.2806. Min Range: -4.2806

Max Act: 2.3768. Min Act: -0.0000

Data Index: 263416 (C4 (Web Text))

Max Activating Token Index: 52