Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 199 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.9353. Min Act: -0.1700

Data Index: 877267 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.8415. Min Act: -0.1700

Data Index: 1223596 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.6853. Min Act: -0.1700

Data Index: 211822 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.7165. Min Act: -0.1700

Data Index: 1171481 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.6853. Min Act: -0.1700

Data Index: 929374 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.6853. Min Act: -0.1700

Data Index: 796691 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.6540. Min Act: -0.1700

Data Index: 1002831 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.6228. Min Act: -0.1700

Data Index: 1195218 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5915. Min Act: -0.1700

Data Index: 1332933 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.6228. Min Act: -0.1700

Data Index: 1347795 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5915. Min Act: -0.1700

Data Index: 246160 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5915. Min Act: -0.1700

Data Index: 122850 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5915. Min Act: -0.1700

Data Index: 985048 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5290. Min Act: -0.1700

Data Index: 1344729 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5290. Min Act: -0.1700

Data Index: 276537 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5603. Min Act: -0.1700

Data Index: 915147 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5915. Min Act: -0.1700

Data Index: 185881 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5603. Min Act: -0.1700

Data Index: 151836 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5603. Min Act: -0.1700

Data Index: 864583 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 5.9353. Min Range: -5.9353

Max Act: 5.5290. Min Act: -0.1700

Data Index: 1342005 (C4 (Web Text))

Max Activating Token Index: 852