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

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

Neuron 4287 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6840. Min Act: -0.0002

Data Index: 700291 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5889. Min Act: -0.0002

Data Index: 666478 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6742. Min Act: -0.0002

Data Index: 984805 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5686. Min Act: -0.0002

Data Index: 659684 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4915. Min Act: -0.0002

Data Index: 198485 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.3479. Min Act: -0.0002

Data Index: 571756 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6232. Min Act: -0.0002

Data Index: 268532 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6884. Min Act: -0.0002

Data Index: 354988 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5081. Min Act: -0.0002

Data Index: 782951 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5770. Min Act: -0.0002

Data Index: 837124 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.5751. Min Act: -0.0002

Data Index: 344593 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6232. Min Act: -0.0002

Data Index: 566842 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4865. Min Act: -0.0002

Data Index: 794843 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.8880. Min Act: -0.0002

Data Index: 1325926 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.7025. Min Act: -0.0002

Data Index: 557324 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4705. Min Act: -0.0002

Data Index: 651038 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.6125. Min Act: -0.0002

Data Index: 1063847 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4138. Min Act: -0.0002

Data Index: 188653 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.3802. Min Act: -0.0002

Data Index: 781603 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 1.8880. Min Range: -1.8880

Max Act: 1.4217. Min Act: -0.0002

Data Index: 147946 (C4 (Web Text))

Max Activating Token Index: 195