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

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

Neuron 1710 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: 0.2109. Min Range: -0.2109

Max Act: 0.2109. Min Act: -0.0002

Data Index: 1222947 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1975. Min Act: -0.0002

Data Index: 539124 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1952. Min Act: -0.0002

Data Index: 105930 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1904. Min Act: -0.0002

Data Index: 328625 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1939. Min Act: -0.0002

Data Index: 155099 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1961. Min Act: -0.0002

Data Index: 746837 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1892. Min Act: -0.0002

Data Index: 209312 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1916. Min Act: -0.0002

Data Index: 428404 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1893. Min Act: -0.0002

Data Index: 972247 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1868. Min Act: -0.0002

Data Index: 941352 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1877. Min Act: -0.0002

Data Index: 1030610 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1925. Min Act: -0.0003

Data Index: 94909 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1885. Min Act: -0.0002

Data Index: 1331589 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1878. Min Act: -0.0002

Data Index: 1172869 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1892. Min Act: -0.0002

Data Index: 812217 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1876. Min Act: -0.0003

Data Index: 1247199 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1838. Min Act: -0.0002

Data Index: 234817 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1869. Min Act: -0.0003

Data Index: 1107242 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1821. Min Act: -0.0002

Data Index: 564600 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1876. Min Act: -0.0003

Data Index: 742152 (C4 (Web Text))

Max Activating Token Index: 754