Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3922 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0193. Min Range: -1.0193

Max Act: 1.0193. Min Act: -0.0002

Data Index: 883792 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.9563. Min Act: -0.0002

Data Index: 120415 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.9200. Min Act: -0.0002

Data Index: 581812 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.9231. Min Act: -0.0002

Data Index: 1195616 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8855. Min Act: -0.0001

Data Index: 1178498 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.9170. Min Act: -0.0001

Data Index: 321944 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8763. Min Act: -0.0001

Data Index: 247338 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.9000. Min Act: -0.0002

Data Index: 138449 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8561. Min Act: -0.0001

Data Index: 191118 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8797. Min Act: -0.0002

Data Index: 935161 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8440. Min Act: -0.0001

Data Index: 252136 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8051. Min Act: -0.0002

Data Index: 1317261 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8551. Min Act: -0.0001

Data Index: 374786 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8258. Min Act: -0.0001

Data Index: 1024649 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8151. Min Act: -0.0002

Data Index: 569517 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.7964. Min Act: -0.0001

Data Index: 495168 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8501. Min Act: -0.0002

Data Index: 646369 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.7847. Min Act: -0.0001

Data Index: 616781 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.7816. Min Act: -0.0002

Data Index: 911659 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.0193. Min Range: -1.0193

Max Act: 0.8082. Min Act: -0.0002

Data Index: 972548 (C4 (Web Text))

Max Activating Token Index: 195