Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1454 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1343412 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1097160 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0853. Min Act: -0.0002

Data Index: 903655 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0002

Data Index: 191517 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0887. Min Act: -0.0002

Data Index: 509212 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0946. Min Act: -0.0002

Data Index: 761438 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0806. Min Act: -0.0002

Data Index: 245861 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0966. Min Act: -0.0002

Data Index: 169234 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0912. Min Act: -0.0002

Data Index: 125690 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0851. Min Act: -0.0002

Data Index: 145840 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0820. Min Act: -0.0002

Data Index: 626183 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0853. Min Act: -0.0002

Data Index: 974390 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0864. Min Act: -0.0002

Data Index: 374536 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0886. Min Act: -0.0002

Data Index: 208286 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0882. Min Act: -0.0002

Data Index: 970802 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0821. Min Act: -0.0002

Data Index: 399250 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1201174 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1272923 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0853. Min Act: -0.0002

Data Index: 926788 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1191274 (C4 (Web Text))

Max Activating Token Index: 234