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

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

Neuron 4650 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: 0.4689. Min Range: -0.4689

Max Act: 0.4689. Min Act: -0.0000

Data Index: 662271 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4193. Min Act: -0.0000

Data Index: 13944 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3928. Min Act: -0.0000

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3879. Min Act: -0.0000

Data Index: 481047 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3542. Min Act: -0.0000

Data Index: 232463 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3131. Min Act: -0.0000

Data Index: 311106 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3124. Min Act: -0.0000

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1061298 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2984. Min Act: -0.0000

Data Index: 475139 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3148. Min Act: -0.0000

Data Index: 704550 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2949. Min Act: -0.0000

Data Index: 671486 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3045. Min Act: -0.0000

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1272 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1244487 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2811. Min Act: -0.0000

Data Index: 527743 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2667. Min Act: -0.0000

Data Index: 27188 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1141326 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2518. Min Act: -0.0000

Data Index: 22055 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2709. Min Act: -0.0000

Data Index: 368146 (C4 (Web Text))

Max Activating Token Index: 602