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

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

Neuron 5424 in Layer 0

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: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1099586 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1207. Min Act: 0.0001

Data Index: 406700 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1245728 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1026. Min Act: 0.0001

Data Index: 1281228 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1027. Min Act: 0.0001

Data Index: 105894 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1354968 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0983. Min Act: -0.0000

Data Index: 125161 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0924. Min Act: 0.0001

Data Index: 345499 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0926. Min Act: -0.0001

Data Index: 584219 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0912. Min Act: -0.0000

Data Index: 294841 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0892. Min Act: -0.0001

Data Index: 729902 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0905. Min Act: -0.0000

Data Index: 321593 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1028535 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1331535 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0884. Min Act: -0.0001

Data Index: 327442 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0879. Min Act: -0.0000

Data Index: 48696 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0890. Min Act: -0.0001

Data Index: 266466 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0844. Min Act: 0.0002

Data Index: 490891 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0853. Min Act: -0.0001

Data Index: 964938 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0840. Min Act: 0.0001

Data Index: 864840 (C4 (Web Text))

Max Activating Token Index: 758