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

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

Neuron 1340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.2467. Min Act: -0.0000

Data Index: 618226 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.2928. Min Act: -0.0000

Data Index: 775459 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.3798. Min Act: -0.0000

Data Index: 517432 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.2797. Min Act: -0.0000

Data Index: 968993 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.3256. Min Act: -0.0000

Data Index: 376481 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1837. Min Act: -0.0000

Data Index: 483727 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1010970 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1050451 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.3957. Min Act: -0.0000

Data Index: 1044775 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.3062. Min Act: -0.0000

Data Index: 670881 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1352449 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.2555. Min Act: -0.0000

Data Index: 878302 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 1.3957. Min Range: -1.3957

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1083880 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1837. Min Act: -0.0000

Data Index: 158691 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1094. Min Act: -0.0000

Data Index: 230606 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1072779 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.0337. Min Act: -0.0000

Data Index: 808805 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1429. Min Act: -0.0000

Data Index: 697718 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1688. Min Act: -0.0000

Data Index: 996358 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.3957. Min Range: -1.3957

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1125231 (C4 (Web Text))

Max Activating Token Index: 97