Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1234 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1490552 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1549122 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1454960 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1529952 (Python Code)

Max Activating Token Index: 299

Text #4

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1466929 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1415561 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1551327 (Python Code)

Max Activating Token Index: 433

Text #7

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1538378 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1509645 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1384921 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1406622 (Python Code)

Max Activating Token Index: 569

Text #11

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1553170 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1635274 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1497328 (Python Code)

Max Activating Token Index: 395

Text #14

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1392784 (Python Code)

Max Activating Token Index: 582

Text #15

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1508343 (Python Code)

Max Activating Token Index: 869

Text #16

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1381837 (Python Code)

Max Activating Token Index: 314

Text #17

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1456157 (Python Code)

Max Activating Token Index: 298

Text #18

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1437980 (Python Code)

Max Activating Token Index: 937

Text #19

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1455146 (Python Code)

Max Activating Token Index: 234