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

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

Neuron 3638 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1128782 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1126. Min Act: -0.0001

Data Index: 540193 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1247802 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0928. Min Act: -0.0001

Data Index: 479895 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1098. Min Act: -0.0001

Data Index: 494474 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1152. Min Act: -0.0001

Data Index: 119226 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1007. Min Act: -0.0001

Data Index: 524483 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1413415 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1004. Min Act: -0.0001

Data Index: 201707 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0950. Min Act: -0.0001

Data Index: 241366 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1229603 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1001. Min Act: -0.0001

Data Index: 811984 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0998. Min Act: -0.0001

Data Index: 218476 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1030. Min Act: -0.0001

Data Index: 229551 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1003. Min Act: -0.0001

Data Index: 491149 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0944. Min Act: -0.0001

Data Index: 913776 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1605907 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1492533 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1007. Min Act: -0.0001

Data Index: 316082 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1451468 (Python Code)

Max Activating Token Index: 538