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

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

Neuron 3431 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: 1.0913. Min Range: -1.0913

Max Act: 1.0913. Min Act: -0.0002

Data Index: 989436 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 1.0913. Min Range: -1.0913

Max Act: 1.0900. Min Act: -0.0002

Data Index: 1328170 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.0913. Min Range: -1.0913

Max Act: 1.0779. Min Act: -0.0002

Data Index: 1039446 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.0913. Min Range: -1.0913

Max Act: 1.0577. Min Act: -0.0002

Data Index: 351429 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.0913. Min Range: -1.0913

Max Act: 1.0073. Min Act: -0.0003

Data Index: 330498 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9862. Min Act: -0.0002

Data Index: 651909 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9628. Min Act: -0.0002

Data Index: 1241814 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9655. Min Act: -0.0002

Data Index: 1338869 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9689. Min Act: -0.0003

Data Index: 570695 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9251. Min Act: -0.0002

Data Index: 288712 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9404. Min Act: -0.0002

Data Index: 1327150 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9487. Min Act: -0.0003

Data Index: 990882 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9287. Min Act: -0.0002

Data Index: 456571 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9244. Min Act: -0.0002

Data Index: 441078 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9186. Min Act: -0.0002

Data Index: 1130042 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9176. Min Act: -0.0002

Data Index: 666894 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9074. Min Act: -0.0002

Data Index: 1155860 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9091. Min Act: -0.0002

Data Index: 138985 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8840. Min Act: -0.0002

Data Index: 903457 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8937. Min Act: -0.0002

Data Index: 350982 (C4 (Web Text))

Max Activating Token Index: 604