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

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

Neuron 4888 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0961. Min Act: -0.0002

Data Index: 252166 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0972. Min Act: -0.0002

Data Index: 721110 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0971. Min Act: -0.0002

Data Index: 828074 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0938. Min Act: -0.0002

Data Index: 328225 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0902. Min Act: -0.0002

Data Index: 888129 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0932. Min Act: -0.0003

Data Index: 288497 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0875. Min Act: -0.0002

Data Index: 590410 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1030884 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0871. Min Act: -0.0002

Data Index: 120365 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0876. Min Act: -0.0002

Data Index: 142110 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0870. Min Act: -0.0002

Data Index: 738901 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0863. Min Act: -0.0002

Data Index: 349569 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0855. Min Act: -0.0002

Data Index: 866396 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1150405 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0871. Min Act: -0.0002

Data Index: 199693 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0837. Min Act: -0.0003

Data Index: 939664 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0839. Min Act: -0.0002

Data Index: 120008 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0830. Min Act: -0.0002

Data Index: 107436 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0816. Min Act: -0.0002

Data Index: 691759 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0810. Min Act: -0.0002

Data Index: 162052 (C4 (Web Text))

Max Activating Token Index: 524