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

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

Neuron 3213 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0003

Data Index: 833320 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1004. Min Act: -0.0003

Data Index: 1101893 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1018. Min Act: -0.0003

Data Index: 761819 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1011. Min Act: -0.0003

Data Index: 1122171 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0899. Min Act: -0.0003

Data Index: 839171 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0945. Min Act: -0.0003

Data Index: 1304091 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0974. Min Act: -0.0003

Data Index: 639379 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1005. Min Act: -0.0003

Data Index: 761337 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0898. Min Act: -0.0003

Data Index: 805969 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0958. Min Act: -0.0003

Data Index: 289654 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0867. Min Act: -0.0003

Data Index: 375754 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0861. Min Act: -0.0003

Data Index: 1054019 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1002. Min Act: -0.0003

Data Index: 305925 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0924. Min Act: -0.0004

Data Index: 1088059 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0887. Min Act: -0.0003

Data Index: 1242915 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0851. Min Act: -0.0004

Data Index: 917854 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0873. Min Act: -0.0003

Data Index: 766946 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0880. Min Act: -0.0003

Data Index: 216846 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0842. Min Act: -0.0003

Data Index: 85509 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0836. Min Act: -0.0003

Data Index: 530697 (C4 (Web Text))

Max Activating Token Index: 721