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

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

Neuron 2245 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.6042. Min Act: -0.0000

Data Index: 654264 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4770. Min Act: -0.0000

Data Index: 152565 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4647. Min Act: -0.0000

Data Index: 857831 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1257687 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4338. Min Act: -0.0000

Data Index: 904578 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4048. Min Act: -0.0000

Data Index: 425824 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4226. Min Act: -0.0000

Data Index: 547524 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3975. Min Act: -0.0000

Data Index: 15806 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1242305 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3815. Min Act: -0.0000

Data Index: 472651 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1310915 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3888. Min Act: -0.0000

Data Index: 379148 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1083580 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1118613 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3891. Min Act: -0.0000

Data Index: 253685 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3685. Min Act: -0.0000

Data Index: 878480 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3621. Min Act: -0.0000

Data Index: 694484 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1243594 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.3702. Min Act: -0.0000

Data Index: 376285 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.6042. Min Range: -0.6042

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1151035 (C4 (Web Text))

Max Activating Token Index: 156