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

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

Neuron 30 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: 5.3462. Min Range: -5.3462

Max Act: 5.3462. Min Act: -0.1700

Data Index: 972137 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.3462. Min Act: -0.1700

Data Index: 377125 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.3149. Min Act: -0.1700

Data Index: 560498 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.2837. Min Act: -0.1700

Data Index: 212873 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1899. Min Act: -0.1700

Data Index: 27720 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1587. Min Act: -0.1700

Data Index: 840263 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.2212. Min Act: -0.1700

Data Index: 10363 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1899. Min Act: -0.1700

Data Index: 84949 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.2212. Min Act: -0.1700

Data Index: 1114870 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1587. Min Act: -0.1700

Data Index: 972437 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1587. Min Act: -0.1700

Data Index: 69166 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1587. Min Act: -0.1700

Data Index: 837973 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1274. Min Act: -0.1700

Data Index: 163501 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1587. Min Act: -0.1700

Data Index: 716483 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1587. Min Act: -0.1700

Data Index: 1352496 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1587. Min Act: -0.1700

Data Index: 875102 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1274. Min Act: -0.1700

Data Index: 1331633 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.0962. Min Act: -0.1700

Data Index: 965882 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1274. Min Act: -0.1700

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1899. Min Act: -0.1700

Data Index: 428983 (C4 (Web Text))

Max Activating Token Index: 959