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

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

Neuron 4570 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: 0.1057. Min Range: -0.1057

Max Act: 0.1057. Min Act: -0.0002

Data Index: 242469 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1248647 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0986. Min Act: -0.0003

Data Index: 1020928 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0978. Min Act: -0.0002

Data Index: 583181 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0960. Min Act: -0.0002

Data Index: 943558 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1268441 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0975. Min Act: -0.0002

Data Index: 808611 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0948. Min Act: -0.0002

Data Index: 112179 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0958. Min Act: -0.0003

Data Index: 174768 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0923. Min Act: -0.0002

Data Index: 23677 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0924. Min Act: -0.0002

Data Index: 667918 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1034248 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0929. Min Act: -0.0003

Data Index: 1002443 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1185286 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0935. Min Act: -0.0002

Data Index: 899768 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0936. Min Act: -0.0002

Data Index: 712867 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0938. Min Act: -0.0003

Data Index: 454895 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0921. Min Act: -0.0002

Data Index: 104971 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0896. Min Act: -0.0002

Data Index: 96734 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0922. Min Act: -0.0002

Data Index: 781450 (C4 (Web Text))

Max Activating Token Index: 240