Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2846 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3930. Min Act: -0.0001

Data Index: 59776 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3212. Min Act: -0.0001

Data Index: 508130 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3100. Min Act: -0.0001

Data Index: 203022 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3216. Min Act: -0.0001

Data Index: 45567 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2973. Min Act: -0.0001

Data Index: 717282 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2994. Min Act: -0.0001

Data Index: 470562 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3007. Min Act: -0.0001

Data Index: 347975 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2987. Min Act: -0.0001

Data Index: 186445 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1185744 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2954. Min Act: -0.0001

Data Index: 709193 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1343408 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2828. Min Act: -0.0001

Data Index: 1145939 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2522. Min Act: -0.0001

Data Index: 829255 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1162640 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2681. Min Act: -0.0001

Data Index: 680070 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2655. Min Act: -0.0001

Data Index: 502570 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2540. Min Act: -0.0001

Data Index: 543166 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2715. Min Act: -0.0001

Data Index: 775749 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1105236 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2630. Min Act: -0.0001

Data Index: 308896 (C4 (Web Text))

Max Activating Token Index: 713