Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.5225. Min Range: -7.5225

Max Act: 7.5225. Min Act: -0.1700

Data Index: 772596 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 7.5225. Min Range: -7.5225

Max Act: 7.3975. Min Act: -0.1700

Data Index: 208119 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 7.5225. Min Range: -7.5225

Max Act: 7.3350. Min Act: -0.1700

Data Index: 52821 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 7.5225. Min Range: -7.5225

Max Act: 7.2413. Min Act: -0.1700

Data Index: 46570 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 7.5225. Min Range: -7.5225

Max Act: 7.0538. Min Act: -0.1700

Data Index: 504125 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.9600. Min Act: -0.1700

Data Index: 1017727 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.8038. Min Act: -0.1700

Data Index: 977597 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 7.5225. Min Range: -7.5225

Max Act: 7.0850. Min Act: -0.1700

Data Index: 493290 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.9600. Min Act: -0.1700

Data Index: 32986 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.9600. Min Act: -0.1700

Data Index: 629156 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.8663. Min Act: -0.1700

Data Index: 70629 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.8663. Min Act: -0.1700

Data Index: 1291458 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.7413. Min Act: -0.1700

Data Index: 1346276 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.7725. Min Act: -0.1700

Data Index: 1247268 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.7725. Min Act: -0.1700

Data Index: 968642 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.8038. Min Act: -0.1700

Data Index: 240030 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.8038. Min Act: -0.1700

Data Index: 297806 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.8350. Min Act: -0.1700

Data Index: 215501 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.5538. Min Act: -0.1700

Data Index: 905607 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 7.5225. Min Range: -7.5225

Max Act: 6.7725. Min Act: -0.1700

Data Index: 764753 (C4 (Web Text))

Max Activating Token Index: 450