Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1851 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1245. Min Act: -0.0002

Data Index: 185013 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1169. Min Act: -0.0002

Data Index: 32833 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1168. Min Act: -0.0002

Data Index: 252392 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1144. Min Act: -0.0002

Data Index: 958400 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1303468 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1086. Min Act: -0.0002

Data Index: 85681 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1089. Min Act: -0.0002

Data Index: 763577 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1050967 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1115530 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1073. Min Act: -0.0002

Data Index: 536923 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1293940 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1212317 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1000318 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1293172 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1077. Min Act: -0.0002

Data Index: 383066 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0997. Min Act: -0.0002

Data Index: 621880 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1036. Min Act: -0.0002

Data Index: 712582 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1018. Min Act: -0.0002

Data Index: 271316 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1050. Min Act: -0.0002

Data Index: 604000 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1002. Min Act: -0.0002

Data Index: 1293313 (C4 (Web Text))

Max Activating Token Index: 821