Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3801 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1289. Min Act: -0.0002

Data Index: 10001 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1388. Min Act: -0.0002

Data Index: 688894 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1019. Min Act: -0.0003

Data Index: 694569 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1217501 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1116. Min Act: -0.0003

Data Index: 516300 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1143. Min Act: -0.0003

Data Index: 1077776 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1064. Min Act: -0.0002

Data Index: 165136 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1039. Min Act: -0.0003

Data Index: 1108117 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0995. Min Act: -0.0003

Data Index: 868365 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1028. Min Act: -0.0003

Data Index: 1271794 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1025. Min Act: -0.0003

Data Index: 834107 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1061. Min Act: -0.0003

Data Index: 1166324 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0983. Min Act: -0.0003

Data Index: 807279 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1053. Min Act: -0.0003

Data Index: 2991 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1005. Min Act: -0.0003

Data Index: 978915 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1002. Min Act: -0.0002

Data Index: 791733 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1027. Min Act: -0.0003

Data Index: 288591 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0985. Min Act: -0.0003

Data Index: 40801 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1006. Min Act: -0.0003

Data Index: 786661 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0970. Min Act: -0.0002

Data Index: 488915 (C4 (Web Text))

Max Activating Token Index: 107