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

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

Neuron 4326 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: 0.7012. Min Range: -0.7012

Max Act: 0.7012. Min Act: -0.0000

Data Index: 693767 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5543. Min Act: -0.0000

Data Index: 733858 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1244113 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4677. Min Act: -0.0000

Data Index: 999584 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1028121 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4930. Min Act: -0.0000

Data Index: 839891 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4965. Min Act: -0.0000

Data Index: 663308 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4775. Min Act: -0.0000

Data Index: 38444 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4916. Min Act: -0.0000

Data Index: 496555 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4564. Min Act: -0.0000

Data Index: 895950 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4876. Min Act: -0.0000

Data Index: 186071 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4415. Min Act: -0.0000

Data Index: 610094 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4119. Min Act: -0.0000

Data Index: 917077 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4578. Min Act: -0.0000

Data Index: 840957 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4418. Min Act: -0.0000

Data Index: 479394 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4461. Min Act: -0.0000

Data Index: 503790 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4433. Min Act: -0.0000

Data Index: 334930 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4710. Min Act: -0.0000

Data Index: 692928 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4509. Min Act: -0.0000

Data Index: 955507 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4680. Min Act: -0.0000

Data Index: 250504 (C4 (Web Text))

Max Activating Token Index: 149