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

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

Neuron 686 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: 0.1448. Min Range: -0.1448

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1255077 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1075432 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1195. Min Act: -0.0001

Data Index: 683220 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1481765 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1572770 (Python Code)

Max Activating Token Index: 713

Text #5

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1243. Min Act: -0.0001

Data Index: 810411 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1152. Min Act: -0.0001

Data Index: 546015 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1076365 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1582256 (Python Code)

Max Activating Token Index: 151

Text #9

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1525073 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1155. Min Act: -0.0001

Data Index: 295880 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1130. Min Act: -0.0001

Data Index: 138415 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1607664 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1193. Min Act: -0.0001

Data Index: 759973 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1442146 (Python Code)

Max Activating Token Index: 727

Text #15

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1595833 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1595991 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1419524 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1129. Min Act: -0.0001

Data Index: 943791 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1453473 (Python Code)

Max Activating Token Index: 205