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

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

Neuron 1943 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: 3.9007. Min Range: -3.9007

Max Act: 3.9007. Min Act: -0.1700

Data Index: 1046931 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.8068. Min Act: -0.1700

Data Index: 394391 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.7443. Min Act: -0.1700

Data Index: 706783 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.7130. Min Act: -0.1700

Data Index: 605907 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.6504. Min Act: -0.1700

Data Index: 597857 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.6504. Min Act: -0.1700

Data Index: 98011 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.6191. Min Act: -0.1700

Data Index: 1071989 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.6191. Min Act: -0.1700

Data Index: 793206 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5564. Min Act: -0.1700

Data Index: 762924 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5408. Min Act: -0.1700

Data Index: 1120258 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5251. Min Act: -0.1700

Data Index: 635404 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5094. Min Act: -0.1700

Data Index: 485217 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5408. Min Act: -0.1700

Data Index: 1231801 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.4781. Min Act: -0.1700

Data Index: 763170 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5251. Min Act: -0.1700

Data Index: 1185905 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5408. Min Act: -0.1700

Data Index: 205917 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5094. Min Act: -0.1700

Data Index: 1108905 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.4938. Min Act: -0.1700

Data Index: 565113 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.5094. Min Act: -0.1700

Data Index: 1114148 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 3.9007. Min Range: -3.9007

Max Act: 3.4781. Min Act: -0.1700

Data Index: 533251 (C4 (Web Text))

Max Activating Token Index: 705