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

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

Neuron 4787 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: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0002

Data Index: 101717 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1022489 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1214002 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1126. Min Act: -0.0002

Data Index: 725169 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1115. Min Act: -0.0002

Data Index: 479540 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1260766 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1126. Min Act: -0.0002

Data Index: 759060 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1055139 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1073. Min Act: -0.0002

Data Index: 928624 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1104. Min Act: -0.0002

Data Index: 171742 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1063. Min Act: -0.0002

Data Index: 659222 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1018. Min Act: -0.0002

Data Index: 212389 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1087. Min Act: -0.0002

Data Index: 734095 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1048. Min Act: -0.0002

Data Index: 40622 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1007. Min Act: -0.0002

Data Index: 822750 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1032. Min Act: -0.0002

Data Index: 700188 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1101227 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1032. Min Act: -0.0002

Data Index: 274211 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1033. Min Act: -0.0002

Data Index: 957135 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1034. Min Act: -0.0002

Data Index: 692370 (C4 (Web Text))

Max Activating Token Index: 461