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

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

Neuron 3834 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1265. Min Act: -0.0002

Data Index: 493301 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1222. Min Act: -0.0002

Data Index: 414034 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1171. Min Act: -0.0002

Data Index: 672492 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1068. Min Act: -0.0003

Data Index: 964363 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1147062 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0968. Min Act: -0.0002

Data Index: 808819 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1065. Min Act: -0.0003

Data Index: 1026637 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1039. Min Act: -0.0002

Data Index: 498762 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1003. Min Act: -0.0003

Data Index: 92028 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1197828 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0951. Min Act: -0.0002

Data Index: 661376 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0981. Min Act: -0.0002

Data Index: 508251 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0976. Min Act: -0.0002

Data Index: 542127 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0936. Min Act: -0.0002

Data Index: 611555 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0959. Min Act: -0.0003

Data Index: 1486549 (Python Code)

Max Activating Token Index: 814

Text #15

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0930. Min Act: -0.0003

Data Index: 1153287 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0984. Min Act: -0.0002

Data Index: 128257 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1603722 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0948. Min Act: -0.0003

Data Index: 586372 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0972. Min Act: -0.0003

Data Index: 1612622 (Python Code)

Max Activating Token Index: 727