Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1153 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1823. Min Act: -0.0000

Data Index: 887943 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1188403 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1228. Min Act: -0.0000

Data Index: 39124 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1221. Min Act: -0.0000

Data Index: 743070 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1127190 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1057. Min Act: -0.0000

Data Index: 550834 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1130. Min Act: -0.0000

Data Index: 547894 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1030. Min Act: -0.0000

Data Index: 744014 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1118. Min Act: -0.0000

Data Index: 676640 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1013. Min Act: -0.0000

Data Index: 446344 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0975. Min Act: -0.0000

Data Index: 748180 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0998. Min Act: -0.0000

Data Index: 578418 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0981. Min Act: -0.0000

Data Index: 307762 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0890. Min Act: -0.0000

Data Index: 255471 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1054408 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0915. Min Act: -0.0000

Data Index: 364838 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1197979 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0917. Min Act: -0.0000

Data Index: 906881 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.0876. Min Act: -0.0000

Data Index: 829200 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1196. Min Act: -0.0000

Data Index: 837207 (C4 (Web Text))

Max Activating Token Index: 247