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

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

Neuron 421 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.5664. Min Act: -0.1700

Data Index: 206830 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.4097. Min Act: -0.1700

Data Index: 854613 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.3940. Min Act: -0.1700

Data Index: 931917 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.3783. Min Act: -0.1700

Data Index: 1252767 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.3470. Min Act: -0.1700

Data Index: 939468 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.3470. Min Act: -0.1700

Data Index: 1272571 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.3313. Min Act: -0.1700

Data Index: 755826 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.3313. Min Act: -0.1700

Data Index: 674830 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.3313. Min Act: -0.1700

Data Index: 29696 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2999. Min Act: -0.1700

Data Index: 446344 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2999. Min Act: -0.1700

Data Index: 755132 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.3156. Min Act: -0.1700

Data Index: 926300 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2841. Min Act: -0.1700

Data Index: 467112 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2841. Min Act: -0.1700

Data Index: 128410 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2999. Min Act: -0.1700

Data Index: 1310854 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2999. Min Act: -0.1700

Data Index: 1345066 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2841. Min Act: -0.1700

Data Index: 273325 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2999. Min Act: -0.1700

Data Index: 835923 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2684. Min Act: -0.1700

Data Index: 617799 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 3.5664. Min Range: -3.5664

Max Act: 3.2527. Min Act: -0.1700

Data Index: 1138305 (C4 (Web Text))

Max Activating Token Index: 437