Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1380 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1362. Min Act: -0.0003

Data Index: 1200321 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1300. Min Act: -0.0003

Data Index: 937517 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1208. Min Act: -0.0003

Data Index: 779495 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1149. Min Act: -0.0003

Data Index: 257705 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1123. Min Act: -0.0003

Data Index: 164261 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1062. Min Act: -0.0003

Data Index: 898749 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1128. Min Act: -0.0003

Data Index: 1179916 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1073. Min Act: -0.0003

Data Index: 271305 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1147. Min Act: -0.0003

Data Index: 1019654 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1100. Min Act: -0.0003

Data Index: 119953 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1007. Min Act: -0.0003

Data Index: 38294 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1078. Min Act: -0.0003

Data Index: 1291172 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1029. Min Act: -0.0003

Data Index: 888109 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0991. Min Act: -0.0003

Data Index: 1316874 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1021. Min Act: -0.0003

Data Index: 1132317 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0990. Min Act: -0.0003

Data Index: 326336 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0953. Min Act: -0.0003

Data Index: 252824 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1026. Min Act: -0.0003

Data Index: 995576 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1059. Min Act: -0.0003

Data Index: 131750 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0891. Min Act: -0.0003

Data Index: 795895 (C4 (Web Text))

Max Activating Token Index: 559