Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3319 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.6034. Min Act: -0.0001

Data Index: 1043813 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3840. Min Act: -0.0001

Data Index: 772926 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3035. Min Act: -0.0002

Data Index: 594060 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2015. Min Act: -0.0002

Data Index: 232929 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1494. Min Act: -0.0002

Data Index: 1140724 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2068. Min Act: -0.0001

Data Index: 102383 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1377. Min Act: -0.0002

Data Index: 1272387 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1429. Min Act: -0.0002

Data Index: 769105 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1092. Min Act: -0.0002

Data Index: 681995 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0888. Min Act: -0.0002

Data Index: 107673 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0584. Min Act: -0.0002

Data Index: 510448 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0393. Min Act: -0.0002

Data Index: 1001559 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0016. Min Act: -0.0001

Data Index: 275994 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0596. Min Act: -0.0002

Data Index: 537181 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0788. Min Act: -0.0002

Data Index: 303461 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0610. Min Act: -0.0002

Data Index: 1027979 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0484. Min Act: -0.0002

Data Index: 482576 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.6034. Min Range: -1.6034

Max Act: 0.9489. Min Act: -0.0002

Data Index: 630883 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0964. Min Act: -0.0001

Data Index: 602160 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0237. Min Act: -0.0002

Data Index: 851334 (C4 (Web Text))

Max Activating Token Index: 12