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

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

Neuron 2181 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.2868. Min Act: -0.0000

Data Index: 90536 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.3422. Min Act: -0.0000

Data Index: 953389 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1342870 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0898. Min Act: -0.0000

Data Index: 496795 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.1266. Min Act: -0.0000

Data Index: 753455 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.2168. Min Act: -0.0000

Data Index: 497780 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.1949. Min Act: -0.0000

Data Index: 569187 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.8312. Min Act: -0.0000

Data Index: 979676 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0340. Min Act: -0.0000

Data Index: 898061 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1317457 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0549. Min Act: -0.0000

Data Index: 826314 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1111419 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1350031 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.8665. Min Act: -0.0000

Data Index: 769143 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.8869. Min Act: -0.0000

Data Index: 361788 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.8635. Min Act: -0.0000

Data Index: 171725 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.9640. Min Act: -0.0000

Data Index: 831013 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1751 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.8669. Min Act: -0.0000

Data Index: 75418 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.8895. Min Act: -0.0000

Data Index: 627901 (C4 (Web Text))

Max Activating Token Index: 827