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

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

Neuron 2573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0923. Min Act: -0.0000

Data Index: 309398 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.2196. Min Act: -0.0000

Data Index: 1314278 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.2007. Min Act: -0.0000

Data Index: 226126 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.3148. Min Act: -0.0000

Data Index: 264750 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 3.3148. Min Range: -3.3148

Max Act: 2.9730. Min Act: -0.0000

Data Index: 116497 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.1117. Min Act: -0.0000

Data Index: 738158 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0986. Min Act: -0.0000

Data Index: 594787 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0858. Min Act: -0.0000

Data Index: 906010 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0832. Min Act: -0.0000

Data Index: 579730 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0640. Min Act: -0.0000

Data Index: 657777 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0824. Min Act: -0.0000

Data Index: 349855 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.2286. Min Act: -0.0000

Data Index: 536678 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0574. Min Act: -0.0000

Data Index: 603864 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.2075. Min Act: -0.0000

Data Index: 480176 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0425. Min Act: -0.0000

Data Index: 362049 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.1251. Min Act: -0.0000

Data Index: 1268542 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.0955. Min Act: -0.0000

Data Index: 2163 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.3148. Min Range: -3.3148

Max Act: 2.8164. Min Act: -0.0000

Data Index: 418757 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 3.3148. Min Range: -3.3148

Max Act: 2.9433. Min Act: -0.0000

Data Index: 540274 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 3.3148. Min Range: -3.3148

Max Act: 3.1215. Min Act: -0.0000

Data Index: 88801 (C4 (Web Text))

Max Activating Token Index: 308