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

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

Neuron 59 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1375. Min Act: -0.0000

Data Index: 730520 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1219. Min Act: -0.0001

Data Index: 237422 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1203. Min Act: -0.0001

Data Index: 372036 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1235677 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1148. Min Act: -0.0001

Data Index: 823517 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1137. Min Act: -0.0000

Data Index: 668237 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1085. Min Act: -0.0001

Data Index: 498153 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1108. Min Act: -0.0001

Data Index: 653895 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1095. Min Act: -0.0000

Data Index: 710310 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1059. Min Act: -0.0001

Data Index: 859693 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1060. Min Act: -0.0001

Data Index: 266386 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1192446 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0962. Min Act: -0.0000

Data Index: 557912 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0934. Min Act: -0.0000

Data Index: 737839 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1007. Min Act: -0.0001

Data Index: 650094 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0962. Min Act: -0.0001

Data Index: 704070 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1292868 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0952. Min Act: -0.0001

Data Index: 350264 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0911. Min Act: -0.0001

Data Index: 968381 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0964. Min Act: -0.0000

Data Index: 453590 (C4 (Web Text))

Max Activating Token Index: 960