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

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

Neuron 3014 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.5389. Min Act: -0.0000

Data Index: 13946 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.3947. Min Act: -0.0000

Data Index: 883819 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.2508. Min Act: -0.0000

Data Index: 829430 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.1764. Min Act: -0.0000

Data Index: 894202 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.1058. Min Act: -0.0000

Data Index: 946869 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0845. Min Act: -0.0000

Data Index: 899520 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0232. Min Act: -0.0000

Data Index: 848033 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1069741 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0175. Min Act: -0.0000

Data Index: 627610 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9854. Min Act: -0.0000

Data Index: 438515 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9809. Min Act: -0.0000

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1239513 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9727. Min Act: -0.0000

Data Index: 96225 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9454. Min Act: -0.0000

Data Index: 598784 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9300. Min Act: -0.0000

Data Index: 238169 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.8889. Min Act: -0.0000

Data Index: 204881 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.8975. Min Act: -0.0000

Data Index: 631889 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9009. Min Act: -0.0000

Data Index: 901839 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.8969. Min Act: -0.0000

Data Index: 677662 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.8919. Min Act: -0.0000

Data Index: 849866 (C4 (Web Text))

Max Activating Token Index: 271