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

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

Neuron 1418 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: 3.6853. Min Range: -3.6853

Max Act: 3.6853. Min Act: -0.1700

Data Index: 973972 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.6540. Min Act: -0.1700

Data Index: 200290 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.5914. Min Act: -0.1700

Data Index: 507001 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.6853. Min Act: -0.1700

Data Index: 1260665 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4661. Min Act: -0.1700

Data Index: 1267782 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.5758. Min Act: -0.1700

Data Index: 101218 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4504. Min Act: -0.1700

Data Index: 555774 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.5758. Min Act: -0.1700

Data Index: 845816 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.5758. Min Act: -0.1700

Data Index: 1002261 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.5444. Min Act: -0.1700

Data Index: 358092 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4974. Min Act: -0.1700

Data Index: 777160 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4661. Min Act: -0.1700

Data Index: 641535 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4818. Min Act: -0.1700

Data Index: 1151587 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.5131. Min Act: -0.1700

Data Index: 977097 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4818. Min Act: -0.1700

Data Index: 230093 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4661. Min Act: -0.1700

Data Index: 1302388 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4504. Min Act: -0.1700

Data Index: 726146 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4347. Min Act: -0.1700

Data Index: 48770 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.3877. Min Act: -0.1700

Data Index: 581051 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 3.6853. Min Range: -3.6853

Max Act: 3.4818. Min Act: -0.1700

Data Index: 1060978 (C4 (Web Text))

Max Activating Token Index: 193