Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 526 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1381201 (Python Code)

Max Activating Token Index: 214

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1605612 (Python Code)

Max Activating Token Index: 739

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1196088 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1121. Min Act: -0.0001

Data Index: 23097 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1519523 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1099260 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1363241 (Python Code)

Max Activating Token Index: 948

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1055. Min Act: -0.0001

Data Index: 969660 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1065. Min Act: -0.0001

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1477322 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1078. Min Act: -0.0001

Data Index: 522110 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1625336 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1584328 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1562687 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1548034 (Python Code)

Max Activating Token Index: 792

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0997. Min Act: -0.0001

Data Index: 121545 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1514328 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0993. Min Act: -0.0001

Data Index: 669438 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0927. Min Act: -0.0001

Data Index: 603649 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1382427 (Python Code)

Max Activating Token Index: 206