Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 524 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.2417. Min Act: -0.0003

Data Index: 296245 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.0270. Min Act: -0.0003

Data Index: 732536 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.0025. Min Act: -0.0003

Data Index: 17240 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8584. Min Act: -0.0003

Data Index: 929353 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8665. Min Act: -0.0003

Data Index: 839212 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8551. Min Act: -0.0003

Data Index: 820861 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8162. Min Act: -0.0003

Data Index: 175448 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8676. Min Act: -0.0003

Data Index: 930469 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.9187. Min Act: -0.0003

Data Index: 1270449 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.7006. Min Act: -0.0003

Data Index: 905423 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.7737. Min Act: -0.0003

Data Index: 79053 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.7840. Min Act: -0.0003

Data Index: 1288494 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.7878. Min Act: -0.0003

Data Index: 404758 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.7204. Min Act: -0.0003

Data Index: 149770 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.7141. Min Act: -0.0003

Data Index: 333733 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.6506. Min Act: -0.0003

Data Index: 1279635 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.7026. Min Act: -0.0003

Data Index: 977476 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.6903. Min Act: -0.0003

Data Index: 7729 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.6857. Min Act: -0.0003

Data Index: 255824 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.7057. Min Act: -0.0003

Data Index: 1009312 (C4 (Web Text))

Max Activating Token Index: 808