Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3250 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1282. Min Act: -0.0002

Data Index: 614736 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1212. Min Act: -0.0002

Data Index: 516675 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1283. Min Act: -0.0002

Data Index: 314644 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1143. Min Act: -0.0002

Data Index: 789274 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1041. Min Act: -0.0002

Data Index: 729378 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1055. Min Act: -0.0002

Data Index: 223363 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1043. Min Act: -0.0002

Data Index: 239948 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1075. Min Act: -0.0002

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1044. Min Act: -0.0002

Data Index: 374718 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1026. Min Act: -0.0002

Data Index: 970873 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0991. Min Act: -0.0002

Data Index: 242439 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1279053 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1076. Min Act: -0.0002

Data Index: 934511 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1060. Min Act: -0.0002

Data Index: 482301 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1150. Min Act: -0.0002

Data Index: 102594 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1081737 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1014. Min Act: -0.0002

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0920. Min Act: -0.0002

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0983. Min Act: -0.0002

Data Index: 63637 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0994. Min Act: -0.0002

Data Index: 166338 (C4 (Web Text))

Max Activating Token Index: 368