Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3328 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.4853. Min Act: -0.0000

Data Index: 835241 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9477. Min Act: -0.0000

Data Index: 558049 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0101. Min Act: -0.0000

Data Index: 62502 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9819. Min Act: -0.0000

Data Index: 903415 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1316738 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9720. Min Act: -0.0000

Data Index: 7236 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9571. Min Act: -0.0000

Data Index: 112192 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9502. Min Act: -0.0000

Data Index: 559052 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9476. Min Act: -0.0000

Data Index: 420369 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8742. Min Act: -0.0000

Data Index: 314778 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1284058 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8573. Min Act: -0.0000

Data Index: 237960 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1082882 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8544. Min Act: -0.0000

Data Index: 883735 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8908. Min Act: -0.0000

Data Index: 227232 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1048188 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1131019 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8731. Min Act: -0.0000

Data Index: 162059 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1194934 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1016604 (C4 (Web Text))

Max Activating Token Index: 956