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

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

Neuron 1508 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.6096. Min Act: -0.1700

Data Index: 80638 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.5469. Min Act: -0.1700

Data Index: 333239 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.5156. Min Act: -0.1700

Data Index: 1195851 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.5469. Min Act: -0.1700

Data Index: 525468 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.5783. Min Act: -0.1700

Data Index: 1132845 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.5156. Min Act: -0.1700

Data Index: 299344 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4999. Min Act: -0.1700

Data Index: 628366 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4999. Min Act: -0.1700

Data Index: 568062 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4843. Min Act: -0.1700

Data Index: 1326395 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.5156. Min Act: -0.1700

Data Index: 723408 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4372. Min Act: -0.1700

Data Index: 388714 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4372. Min Act: -0.1700

Data Index: 1059900 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4529. Min Act: -0.1700

Data Index: 949521 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4372. Min Act: -0.1700

Data Index: 1201980 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4059. Min Act: -0.1700

Data Index: 1337500 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.3902. Min Act: -0.1700

Data Index: 1282734 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4216. Min Act: -0.1700

Data Index: 722817 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.4216. Min Act: -0.1700

Data Index: 1305678 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.3745. Min Act: -0.1700

Data Index: 724927 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.3588. Min Act: -0.1700

Data Index: 1128046 (C4 (Web Text))

Max Activating Token Index: 581