Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1191 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1203. Min Act: -0.0003

Data Index: 1501315 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1195. Min Act: -0.0003

Data Index: 1566221 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1430265 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1185. Min Act: -0.0003

Data Index: 1587602 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1145. Min Act: -0.0003

Data Index: 1514851 (Python Code)

Max Activating Token Index: 797

Text #5

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1120. Min Act: -0.0003

Data Index: 1580286 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1125. Min Act: -0.0003

Data Index: 1394151 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1147. Min Act: -0.0003

Data Index: 1525736 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1138. Min Act: -0.0003

Data Index: 1637244 (Python Code)

Max Activating Token Index: 622

Text #9

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1626019 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1072. Min Act: -0.0003

Data Index: 1472241 (Python Code)

Max Activating Token Index: 988

Text #11

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1616657 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1053. Min Act: -0.0003

Data Index: 1653995 (Python Code)

Max Activating Token Index: 925

Text #13

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1119. Min Act: -0.0003

Data Index: 1478848 (Python Code)

Max Activating Token Index: 368

Text #14

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1107. Min Act: -0.0003

Data Index: 1589013 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1082. Min Act: -0.0003

Data Index: 1631609 (Python Code)

Max Activating Token Index: 743

Text #16

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1529304 (Python Code)

Max Activating Token Index: 648

Text #17

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1067. Min Act: -0.0003

Data Index: 1483983 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1526054 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1069. Min Act: -0.0003

Data Index: 1430145 (Python Code)

Max Activating Token Index: 987