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

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

Neuron 1769 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.7999. Min Act: -0.1700

Data Index: 155720 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.6749. Min Act: -0.1700

Data Index: 584106 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.7062. Min Act: -0.1700

Data Index: 1029459 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.7062. Min Act: -0.1700

Data Index: 1123843 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.6749. Min Act: -0.1700

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.5812. Min Act: -0.1700

Data Index: 753498 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.5499. Min Act: -0.1700

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.5187. Min Act: -0.1700

Data Index: 486198 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.5499. Min Act: -0.1700

Data Index: 518353 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.5187. Min Act: -0.1700

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.5187. Min Act: -0.1700

Data Index: 929012 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.5187. Min Act: -0.1700

Data Index: 1314142 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.4562. Min Act: -0.1700

Data Index: 284788 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.4562. Min Act: -0.1700

Data Index: 1235730 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.2999. Min Act: -0.1700

Data Index: 358814 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.4874. Min Act: -0.1700

Data Index: 808554 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.5499. Min Act: -0.1700

Data Index: 904491 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.4249. Min Act: -0.1700

Data Index: 328003 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.4562. Min Act: -0.1700

Data Index: 370994 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 5.7999. Min Range: -5.7999

Max Act: 5.3937. Min Act: -0.1700

Data Index: 1078352 (C4 (Web Text))

Max Activating Token Index: 595