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

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

Neuron 4596 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.5316. Min Act: -0.0000

Data Index: 286262 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4655. Min Act: -0.0000

Data Index: 306149 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4927. Min Act: -0.0000

Data Index: 347596 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4824. Min Act: -0.0000

Data Index: 435329 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1269728 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4454. Min Act: -0.0000

Data Index: 742188 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4122. Min Act: -0.0000

Data Index: 102794 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4142. Min Act: -0.0000

Data Index: 724116 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3889. Min Act: -0.0000

Data Index: 558340 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1308356 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3462. Min Act: -0.0000

Data Index: 135724 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3536. Min Act: -0.0000

Data Index: 361359 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3299. Min Act: -0.0000

Data Index: 846687 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3318. Min Act: -0.0000

Data Index: 907543 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3201. Min Act: -0.0000

Data Index: 944339 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1357061 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3069. Min Act: -0.0000

Data Index: 794481 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3289. Min Act: -0.0000

Data Index: 63302 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3211. Min Act: -0.0000

Data Index: 446538 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1285912 (C4 (Web Text))

Max Activating Token Index: 419