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

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

Neuron 3973 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: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0002

Data Index: 497714 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1167143 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1010. Min Act: -0.0002

Data Index: 815151 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0941. Min Act: -0.0002

Data Index: 204721 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1096244 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0884. Min Act: -0.0002

Data Index: 503513 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0937. Min Act: -0.0002

Data Index: 284277 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0851. Min Act: -0.0002

Data Index: 820610 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1174464 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0894. Min Act: -0.0002

Data Index: 641683 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1294777 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0810. Min Act: -0.0001

Data Index: 640526 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0780. Min Act: -0.0002

Data Index: 374065 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0757. Min Act: -0.0002

Data Index: 251634 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0858. Min Act: -0.0001

Data Index: 825636 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0854. Min Act: -0.0002

Data Index: 66411 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0686. Min Act: -0.0001

Data Index: 926793 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0786. Min Act: -0.0001

Data Index: 731643 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1115786 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1119594 (C4 (Web Text))

Max Activating Token Index: 685