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

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

Neuron 5543 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2087. Min Act: -0.0002

Data Index: 389216 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1939. Min Act: -0.0002

Data Index: 945881 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1776. Min Act: -0.0002

Data Index: 423791 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1584. Min Act: -0.0002

Data Index: 623903 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1608. Min Act: -0.0002

Data Index: 638957 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1527. Min Act: -0.0002

Data Index: 1290933 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1516. Min Act: -0.0002

Data Index: 300909 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1388. Min Act: -0.0002

Data Index: 177189 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1053687 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1292. Min Act: -0.0002

Data Index: 561090 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1271165 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1216. Min Act: -0.0002

Data Index: 235515 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1245. Min Act: -0.0002

Data Index: 219671 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1247. Min Act: -0.0002

Data Index: 630310 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1265. Min Act: -0.0002

Data Index: 230759 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1213. Min Act: -0.0002

Data Index: 231998 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1184112 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1344378 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1125. Min Act: -0.0002

Data Index: 228534 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1165. Min Act: -0.0002

Data Index: 612151 (C4 (Web Text))

Max Activating Token Index: 480