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

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

Neuron 1759 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: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0001

Data Index: 517002 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0895. Min Act: -0.0001

Data Index: 820518 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1285096 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0859. Min Act: -0.0001

Data Index: 88866 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0797. Min Act: -0.0002

Data Index: 189210 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0841. Min Act: -0.0002

Data Index: 496575 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0775. Min Act: -0.0001

Data Index: 307390 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0765. Min Act: -0.0001

Data Index: 237573 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0748. Min Act: -0.0002

Data Index: 502916 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0797. Min Act: -0.0002

Data Index: 535959 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1037350 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0731. Min Act: -0.0002

Data Index: 203666 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0914. Min Act: -0.0002

Data Index: 938057 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0770. Min Act: -0.0002

Data Index: 98123 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0784. Min Act: -0.0001

Data Index: 672796 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0745. Min Act: -0.0002

Data Index: 398497 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1062269 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0740. Min Act: -0.0001

Data Index: 886029 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0673. Min Act: -0.0001

Data Index: 823965 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1133176 (C4 (Web Text))

Max Activating Token Index: 59