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

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

Neuron 1566 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1398. Min Act: -0.0000

Data Index: 534938 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1097. Min Act: -0.0000

Data Index: 335723 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1098612 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1141757 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1002. Min Act: -0.0000

Data Index: 139618 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1536593 (Python Code)

Max Activating Token Index: 417

Text #6

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1001. Min Act: -0.0000

Data Index: 398644 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1129788 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0950. Min Act: -0.0000

Data Index: 488784 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0876. Min Act: -0.0000

Data Index: 993499 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0889. Min Act: -0.0000

Data Index: 520311 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0890. Min Act: -0.0000

Data Index: 393945 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0811. Min Act: -0.0000

Data Index: 483156 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0882. Min Act: -0.0000

Data Index: 84880 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1415396 (Python Code)

Max Activating Token Index: 86

Text #15

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1041092 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0878. Min Act: -0.0000

Data Index: 667081 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0843. Min Act: -0.0000

Data Index: 69975 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0833. Min Act: -0.0000

Data Index: 971945 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1111980 (C4 (Web Text))

Max Activating Token Index: 1019