Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 805 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.8937. Min Act: -0.1698

Data Index: 1244675 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.7687. Min Act: -0.1700

Data Index: 735863 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.8000. Min Act: -0.1699

Data Index: 682242 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.7687. Min Act: -0.1700

Data Index: 792685 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.6750. Min Act: -0.1607

Data Index: 792584 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.6125. Min Act: -0.1574

Data Index: 1339492 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5812. Min Act: -0.1700

Data Index: 1296897 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5812. Min Act: -0.1700

Data Index: 978032 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5812. Min Act: -0.1699

Data Index: 213096 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.6125. Min Act: -0.1700

Data Index: 531723 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5812. Min Act: -0.1692

Data Index: 678566 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5500. Min Act: -0.1700

Data Index: 303682 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5500. Min Act: -0.1700

Data Index: 1302496 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5500. Min Act: -0.0010

Data Index: 299004 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5187. Min Act: -0.1698

Data Index: 438519 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5187. Min Act: -0.1700

Data Index: 814496 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.5187. Min Act: -0.1688

Data Index: 1109012 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.4875. Min Act: -0.1700

Data Index: 47761 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.4875. Min Act: -0.1700

Data Index: 663546 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 5.8937. Min Range: -5.8937

Max Act: 5.4875. Min Act: -0.1700

Data Index: 1046266 (C4 (Web Text))

Max Activating Token Index: 410