Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3887 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0791. Min Act: -0.0002

Data Index: 220002 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1316734 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1324386 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0700. Min Act: -0.0002

Data Index: 357761 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1599185 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0698. Min Act: -0.0002

Data Index: 761378 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1193126 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0686. Min Act: -0.0002

Data Index: 175271 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0668. Min Act: -0.0002

Data Index: 546746 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0663. Min Act: -0.0002

Data Index: 781859 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0639. Min Act: -0.0002

Data Index: 493832 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0651. Min Act: -0.0002

Data Index: 152155 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0643. Min Act: -0.0002

Data Index: 968914 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1357072 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0636. Min Act: -0.0002

Data Index: 714673 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1495340 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0636. Min Act: -0.0002

Data Index: 965608 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0628. Min Act: -0.0002

Data Index: 563194 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1192273 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0630. Min Act: -0.0002

Data Index: 508725 (C4 (Web Text))

Max Activating Token Index: 952