Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1568 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1184904 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1354522 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1143. Min Act: -0.0000

Data Index: 226986 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1109. Min Act: -0.0001

Data Index: 634341 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1015. Min Act: -0.0001

Data Index: 400636 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1053. Min Act: -0.0000

Data Index: 775736 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1083. Min Act: -0.0000

Data Index: 266285 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1015. Min Act: -0.0000

Data Index: 332652 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1017. Min Act: -0.0000

Data Index: 169063 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1005. Min Act: -0.0001

Data Index: 89405 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0965. Min Act: -0.0000

Data Index: 402584 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0954. Min Act: -0.0001

Data Index: 143752 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0991. Min Act: -0.0000

Data Index: 663993 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1026. Min Act: -0.0001

Data Index: 890521 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0983. Min Act: -0.0001

Data Index: 243752 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0981. Min Act: -0.0001

Data Index: 694826 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0941. Min Act: -0.0001

Data Index: 674293 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1286624 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1000. Min Act: -0.0000

Data Index: 428600 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1032616 (C4 (Web Text))

Max Activating Token Index: 766