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

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

Neuron 1178 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: 3.9213. Min Range: -3.9213

Max Act: 3.9213. Min Act: -0.1700

Data Index: 907946 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.8588. Min Act: -0.1700

Data Index: 1013341 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.8588. Min Act: -0.1700

Data Index: 177774 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.8275. Min Act: -0.1700

Data Index: 479220 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7962. Min Act: -0.1700

Data Index: 538127 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7962. Min Act: -0.1700

Data Index: 431561 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7962. Min Act: -0.1700

Data Index: 938974 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7962. Min Act: -0.1700

Data Index: 882797 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7649. Min Act: -0.1700

Data Index: 1141413 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7649. Min Act: -0.1700

Data Index: 107242 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6710. Min Act: -0.1700

Data Index: 1064763 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7023. Min Act: -0.1700

Data Index: 380809 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7023. Min Act: -0.1700

Data Index: 255087 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6397. Min Act: -0.1700

Data Index: 565449 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6710. Min Act: -0.1700

Data Index: 857915 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6710. Min Act: -0.1700

Data Index: 688986 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6397. Min Act: -0.1700

Data Index: 433504 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6710. Min Act: -0.1700

Data Index: 795762 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6710. Min Act: -0.1700

Data Index: 334040 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7023. Min Act: -0.1700

Data Index: 68032 (C4 (Web Text))

Max Activating Token Index: 703