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

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

Neuron 1720 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2032. Min Range: -1.2032

Max Act: 1.2032. Min Act: -0.0000

Data Index: 486353 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 1.2032. Min Range: -1.2032

Max Act: 1.0531. Min Act: -0.0000

Data Index: 261081 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.2032. Min Range: -1.2032

Max Act: 1.0069. Min Act: -0.0000

Data Index: 537089 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1597422 (Python Code)

Max Activating Token Index: 261

Text #4

Max Range: 1.2032. Min Range: -1.2032

Max Act: 1.0119. Min Act: -0.0000

Data Index: 510118 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.9682. Min Act: -0.0000

Data Index: 91639 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1497865 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8566. Min Act: -0.0000

Data Index: 533725 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1051609 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1224921 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.9167. Min Act: -0.0000

Data Index: 143066 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.9696. Min Act: -0.0000

Data Index: 980080 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.9174. Min Act: -0.0000

Data Index: 218309 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8600. Min Act: -0.0000

Data Index: 692794 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1148247 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8641. Min Act: -0.0000

Data Index: 206728 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1240496 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8498. Min Act: -0.0000

Data Index: 769203 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8613. Min Act: -0.0000

Data Index: 328955 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 1.2032. Min Range: -1.2032

Max Act: 0.8353. Min Act: -0.0000

Data Index: 832758 (C4 (Web Text))

Max Activating Token Index: 269