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

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

Neuron 1850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.2837. Min Act: -0.1700

Data Index: 837378 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0649. Min Act: -0.1700

Data Index: 312722 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0962. Min Act: -0.1700

Data Index: 673866 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.1587. Min Act: -0.1700

Data Index: 814583 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0962. Min Act: -0.1700

Data Index: 751843 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0962. Min Act: -0.1700

Data Index: 732741 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0962. Min Act: -0.1700

Data Index: 879242 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0649. Min Act: -0.1700

Data Index: 309955 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0337. Min Act: -0.1700

Data Index: 212552 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0337. Min Act: -0.1700

Data Index: 519016 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0649. Min Act: -0.1700

Data Index: 500317 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0024. Min Act: -0.1700

Data Index: 1283566 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 5.2837. Min Range: -5.2837

Max Act: 4.9712. Min Act: -0.1700

Data Index: 971253 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0024. Min Act: -0.1700

Data Index: 1233780 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 5.2837. Min Range: -5.2837

Max Act: 4.9712. Min Act: -0.1700

Data Index: 359906 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0024. Min Act: -0.1700

Data Index: 836075 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 5.2837. Min Range: -5.2837

Max Act: 5.0024. Min Act: -0.1700

Data Index: 423471 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 5.2837. Min Range: -5.2837

Max Act: 4.9712. Min Act: -0.1700

Data Index: 647287 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 5.2837. Min Range: -5.2837

Max Act: 4.9399. Min Act: -0.1700

Data Index: 755092 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 5.2837. Min Range: -5.2837

Max Act: 4.9399. Min Act: -0.1700

Data Index: 451114 (C4 (Web Text))

Max Activating Token Index: 342