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

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

Neuron 1724 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: 0.8209. Min Range: -0.8209

Max Act: 0.8209. Min Act: -0.0001

Data Index: 457564 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.7920. Min Act: -0.0002

Data Index: 1174753 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.7506. Min Act: -0.0001

Data Index: 598099 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.7260. Min Act: -0.0001

Data Index: 55557 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.7187. Min Act: -0.0001

Data Index: 303289 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6080. Min Act: -0.0001

Data Index: 1233121 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6798. Min Act: -0.0002

Data Index: 181415 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6342. Min Act: -0.0001

Data Index: 1108065 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6824. Min Act: -0.0002

Data Index: 1241917 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.7083. Min Act: -0.0001

Data Index: 760661 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1646747 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6263. Min Act: -0.0002

Data Index: 642949 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.5529. Min Act: -0.0002

Data Index: 824844 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6369. Min Act: -0.0002

Data Index: 1340540 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6893. Min Act: -0.0001

Data Index: 100601 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.5614. Min Act: -0.0002

Data Index: 793096 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6532. Min Act: -0.0002

Data Index: 425440 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.6301. Min Act: -0.0001

Data Index: 1555861 (Python Code)

Max Activating Token Index: 944

Text #18

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.5985. Min Act: -0.0001

Data Index: 602258 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.8209. Min Range: -0.8209

Max Act: 0.7041. Min Act: -0.0002

Data Index: 1184796 (C4 (Web Text))

Max Activating Token Index: 793