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

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

Neuron 6032 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: 0.3860. Min Range: -0.3860

Max Act: 0.3860. Min Act: -0.0002

Data Index: 118124 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3505. Min Act: -0.0002

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3217. Min Act: -0.0002

Data Index: 1244138 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3088. Min Act: -0.0001

Data Index: 216569 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3272. Min Act: -0.0001

Data Index: 1094610 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3092. Min Act: -0.0002

Data Index: 1189164 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2951. Min Act: -0.0002

Data Index: 305608 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2862. Min Act: -0.0001

Data Index: 134129 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2909. Min Act: -0.0001

Data Index: 20102 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2981. Min Act: -0.0002

Data Index: 1265700 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2881. Min Act: -0.0002

Data Index: 445893 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2774. Min Act: -0.0002

Data Index: 214308 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2643. Min Act: -0.0002

Data Index: 226851 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2723. Min Act: -0.0002

Data Index: 1045637 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2707. Min Act: -0.0002

Data Index: 275862 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2645. Min Act: -0.0002

Data Index: 546557 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2771. Min Act: -0.0001

Data Index: 801190 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2682. Min Act: -0.0002

Data Index: 8528 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2698. Min Act: -0.0001

Data Index: 641337 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2668. Min Act: -0.0002

Data Index: 1046194 (C4 (Web Text))

Max Activating Token Index: 381