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

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

Neuron 4928 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: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1322119 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0117. Min Act: -0.0002

Data Index: 197254 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1277626 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0106. Min Act: -0.0002

Data Index: 665554 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0115. Min Act: -0.0002

Data Index: 500580 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0111. Min Act: -0.0002

Data Index: 275898 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0109. Min Act: -0.0002

Data Index: 784397 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0105. Min Act: -0.0003

Data Index: 43148 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0095. Min Act: -0.0002

Data Index: 656788 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0106. Min Act: -0.0002

Data Index: 778045 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1252482 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0113. Min Act: -0.0002

Data Index: 969160 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0103. Min Act: -0.0002

Data Index: 299094 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1266570 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1096138 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0100. Min Act: -0.0003

Data Index: 914261 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0098. Min Act: -0.0002

Data Index: 56214 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0104. Min Act: -0.0002

Data Index: 567855 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1324840 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0101. Min Act: -0.0003

Data Index: 659569 (C4 (Web Text))

Max Activating Token Index: 429