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

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

Neuron 4059 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: 0.1338. Min Range: -0.1338

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1540321 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1047726 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1085. Min Act: -0.0001

Data Index: 194604 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1624970 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1460418 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1431856 (Python Code)

Max Activating Token Index: 397

Text #6

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1301135 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1113. Min Act: -0.0001

Data Index: 118651 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1398225 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1419505 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1052. Min Act: -0.0001

Data Index: 806185 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1035. Min Act: -0.0001

Data Index: 312647 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1594496 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1410553 (Python Code)

Max Activating Token Index: 141

Text #14

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1479564 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1058. Min Act: -0.0001

Data Index: 347883 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0903. Min Act: -0.0001

Data Index: 192439 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1219163 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1444223 (Python Code)

Max Activating Token Index: 380

Text #19

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1483005 (Python Code)

Max Activating Token Index: 551