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

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

Neuron 4927 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.1747. Min Act: -0.0001

Data Index: 1356873 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.1547. Min Act: -0.0001

Data Index: 216691 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0349. Min Act: -0.0001

Data Index: 1064385 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0964. Min Act: -0.0001

Data Index: 247006 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0517. Min Act: -0.0001

Data Index: 128726 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9823. Min Act: -0.0001

Data Index: 648227 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9507. Min Act: -0.0001

Data Index: 1291855 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9026. Min Act: -0.0001

Data Index: 710874 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8800. Min Act: -0.0001

Data Index: 49358 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1086569 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9175. Min Act: -0.0001

Data Index: 600670 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8951. Min Act: -0.0001

Data Index: 75351 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1240102 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8931. Min Act: -0.0001

Data Index: 451517 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0002. Min Act: -0.0001

Data Index: 902073 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9342. Min Act: -0.0001

Data Index: 857417 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9107. Min Act: -0.0001

Data Index: 501398 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8119. Min Act: -0.0001

Data Index: 862688 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8861. Min Act: -0.0001

Data Index: 685086 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8282. Min Act: -0.0001

Data Index: 73167 (C4 (Web Text))

Max Activating Token Index: 317