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

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

Neuron 1986 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: 0.1174. Min Range: -0.1174

Max Act: 0.1174. Min Act: -0.0002

Data Index: 923571 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1453389 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1353881 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1224710 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1005299 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1046. Min Act: -0.0002

Data Index: 431535 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1083. Min Act: -0.0002

Data Index: 696274 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1048. Min Act: -0.0002

Data Index: 502745 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1021936 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1016. Min Act: -0.0002

Data Index: 796593 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1003. Min Act: -0.0002

Data Index: 716887 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1209589 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0994. Min Act: -0.0002

Data Index: 787001 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1571657 (Python Code)

Max Activating Token Index: 785

Text #14

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0988. Min Act: -0.0002

Data Index: 513912 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1019. Min Act: -0.0002

Data Index: 407103 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0981. Min Act: -0.0002

Data Index: 799125 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0998. Min Act: -0.0002

Data Index: 560245 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0989. Min Act: -0.0002

Data Index: 827348 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1033944 (C4 (Web Text))

Max Activating Token Index: 447