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

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

Neuron 1836 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1063. Min Act: -0.0001

Data Index: 127775 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1034. Min Act: -0.0001

Data Index: 926654 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1297368 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1199022 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1082013 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1017. Min Act: -0.0001

Data Index: 669119 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0925. Min Act: -0.0001

Data Index: 510361 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0877. Min Act: -0.0001

Data Index: 134742 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0875. Min Act: -0.0001

Data Index: 316223 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0858. Min Act: -0.0001

Data Index: 761990 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0883. Min Act: -0.0001

Data Index: 130009 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0845. Min Act: -0.0001

Data Index: 233082 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0869. Min Act: -0.0001

Data Index: 518067 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0749. Min Act: -0.0001

Data Index: 231192 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1175956 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0741. Min Act: -0.0001

Data Index: 256937 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1153. Min Act: -0.0001

Data Index: 668375 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0738. Min Act: -0.0001

Data Index: 596181 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0716. Min Act: -0.0001

Data Index: 703311 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.0719. Min Act: -0.0001

Data Index: 925624 (C4 (Web Text))

Max Activating Token Index: 669