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

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

Neuron 2984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1770. Min Act: -0.0000

Data Index: 459195 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1528. Min Act: -0.0000

Data Index: 805281 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1605969 (Python Code)

Max Activating Token Index: 179

Text #3

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1688. Min Act: -0.0000

Data Index: 881019 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1714. Min Act: -0.0000

Data Index: 171568 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1501. Min Act: -0.0000

Data Index: 773073 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1293. Min Act: -0.0000

Data Index: 218962 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1357. Min Act: -0.0000

Data Index: 488381 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1259. Min Act: -0.0000

Data Index: 742224 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1304. Min Act: -0.0000

Data Index: 269519 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1160. Min Act: -0.0000

Data Index: 429048 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1140. Min Act: -0.0000

Data Index: 155691 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1145347 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1294904 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1221261 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1110. Min Act: -0.0000

Data Index: 644990 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1052. Min Act: -0.0000

Data Index: 83565 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1075. Min Act: -0.0000

Data Index: 23722 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1252077 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1054. Min Act: -0.0000

Data Index: 128513 (C4 (Web Text))

Max Activating Token Index: 488