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

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

Neuron 663 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2003. Min Range: -2.2003

Max Act: 2.1983. Min Act: -0.0000

Data Index: 273418 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 2.2003. Min Range: -2.2003

Max Act: 2.0946. Min Act: -0.0000

Data Index: 531083 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 2.2003. Min Range: -2.2003

Max Act: 2.2003. Min Act: -0.0000

Data Index: 1039368 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 2.2003. Min Range: -2.2003

Max Act: 2.0733. Min Act: -0.0000

Data Index: 1073479 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8977. Min Act: -0.0000

Data Index: 273956 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 2.2003. Min Range: -2.2003

Max Act: 2.0998. Min Act: -0.0000

Data Index: 594398 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8245. Min Act: -0.0000

Data Index: 134976 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8047. Min Act: -0.0000

Data Index: 320408 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.7652. Min Act: -0.0000

Data Index: 1313580 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8974. Min Act: -0.0000

Data Index: 157929 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8006. Min Act: -0.0000

Data Index: 961609 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8289. Min Act: -0.0000

Data Index: 1021742 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8179. Min Act: -0.0000

Data Index: 317596 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8182. Min Act: -0.0000

Data Index: 1013609 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8138. Min Act: -0.0000

Data Index: 905307 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.9190. Min Act: -0.0000

Data Index: 1356356 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8697. Min Act: -0.0000

Data Index: 671008 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.6553. Min Act: -0.0000

Data Index: 212476 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8294. Min Act: -0.0000

Data Index: 436370 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 2.2003. Min Range: -2.2003

Max Act: 1.8046. Min Act: -0.0000

Data Index: 1259281 (C4 (Web Text))

Max Activating Token Index: 1018