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

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

Neuron 1005 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: 0.6309. Min Range: -0.6309

Max Act: 0.6176. Min Act: 0.0000

Data Index: 269183 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.6309. Min Act: -0.0000

Data Index: 63754 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5672. Min Act: -0.0000

Data Index: 724739 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1210752 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5181. Min Act: -0.0000

Data Index: 260926 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5342. Min Act: -0.0000

Data Index: 86212 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5203. Min Act: -0.0000

Data Index: 446818 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5340. Min Act: 0.0000

Data Index: 501583 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4997. Min Act: 0.0000

Data Index: 269352 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4971. Min Act: -0.0000

Data Index: 143079 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4932. Min Act: -0.0000

Data Index: 522293 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1181493 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4918. Min Act: -0.0000

Data Index: 675519 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4824. Min Act: 0.0000

Data Index: 217450 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4792. Min Act: -0.0000

Data Index: 34933 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4789. Min Act: 0.0001

Data Index: 1025049 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4607. Min Act: -0.0000

Data Index: 968645 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4624. Min Act: 0.0000

Data Index: 1035169 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1196928 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4588. Min Act: 0.0001

Data Index: 557624 (C4 (Web Text))

Max Activating Token Index: 796