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

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

Neuron 4745 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2960. Min Act: -0.0000

Data Index: 804096 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2240. Min Act: -0.0000

Data Index: 880055 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2140. Min Act: -0.0000

Data Index: 852587 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2107. Min Act: -0.0000

Data Index: 880263 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2137. Min Act: -0.0000

Data Index: 12083 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1941. Min Act: -0.0000

Data Index: 665747 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1045267 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1932. Min Act: -0.0000

Data Index: 969790 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1879. Min Act: -0.0000

Data Index: 421080 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1991. Min Act: -0.0000

Data Index: 979301 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1855. Min Act: -0.0000

Data Index: 240259 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1842. Min Act: -0.0000

Data Index: 556361 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1936. Min Act: -0.0000

Data Index: 654389 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1887. Min Act: -0.0000

Data Index: 147598 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1279053 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1811. Min Act: -0.0000

Data Index: 97640 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1731. Min Act: -0.0000

Data Index: 129431 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1831. Min Act: -0.0000

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1788. Min Act: -0.0000

Data Index: 55218 (C4 (Web Text))

Max Activating Token Index: 878