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

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

Neuron 2228 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: 0.1676. Min Range: -0.1676

Max Act: 0.1676. Min Act: -0.0002

Data Index: 1265021 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1346. Min Act: -0.0002

Data Index: 659218 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1318. Min Act: -0.0002

Data Index: 1124675 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1122558 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1212. Min Act: -0.0002

Data Index: 958751 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1152. Min Act: -0.0002

Data Index: 623282 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1114. Min Act: -0.0002

Data Index: 681415 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1219769 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1094. Min Act: -0.0002

Data Index: 31888 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1040. Min Act: -0.0002

Data Index: 741839 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1053. Min Act: -0.0002

Data Index: 260474 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1148129 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1343406 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1265831 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.0998. Min Act: -0.0002

Data Index: 264318 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1076. Min Act: -0.0002

Data Index: 301587 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1248088 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1258363 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.0991. Min Act: -0.0002

Data Index: 976868 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.1676. Min Range: -0.1676

Max Act: 0.0982. Min Act: -0.0002

Data Index: 626510 (C4 (Web Text))

Max Activating Token Index: 751