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

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

Neuron 4423 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1032. Min Act: -0.0002

Data Index: 291002 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0850. Min Act: -0.0002

Data Index: 389052 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0788. Min Act: -0.0002

Data Index: 223263 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0737. Min Act: -0.0002

Data Index: 497590 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1148659 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0736. Min Act: -0.0002

Data Index: 804222 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1046678 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0722. Min Act: -0.0002

Data Index: 214769 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1262356 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0710. Min Act: -0.0002

Data Index: 664939 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0705. Min Act: -0.0002

Data Index: 188758 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0702. Min Act: -0.0002

Data Index: 576815 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0697. Min Act: -0.0002

Data Index: 116229 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0649. Min Act: -0.0002

Data Index: 666 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0688. Min Act: -0.0002

Data Index: 907908 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0686. Min Act: -0.0002

Data Index: 434519 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1227389 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1196595 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0673. Min Act: -0.0002

Data Index: 919599 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0694. Min Act: -0.0002

Data Index: 441266 (C4 (Web Text))

Max Activating Token Index: 277