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

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

Neuron 1591 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: 3.6780. Min Range: -3.6780

Max Act: 3.6780. Min Act: -0.1700

Data Index: 1120300 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.6467. Min Act: -0.1700

Data Index: 39946 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5840. Min Act: -0.1700

Data Index: 725887 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.6467. Min Act: -0.1700

Data Index: 263297 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5997. Min Act: -0.1700

Data Index: 789958 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5684. Min Act: -0.1700

Data Index: 404405 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5840. Min Act: -0.1700

Data Index: 1131911 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5840. Min Act: -0.1700

Data Index: 631670 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5840. Min Act: -0.1700

Data Index: 153518 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5840. Min Act: -0.1700

Data Index: 604230 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5527. Min Act: -0.1700

Data Index: 935046 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5527. Min Act: -0.1700

Data Index: 1177288 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5057. Min Act: -0.1700

Data Index: 1205263 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5370. Min Act: -0.1700

Data Index: 1085339 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5214. Min Act: -0.1700

Data Index: 497523 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5370. Min Act: -0.1700

Data Index: 390338 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5214. Min Act: -0.1700

Data Index: 808333 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5214. Min Act: -0.1700

Data Index: 830651 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5370. Min Act: -0.1700

Data Index: 1143825 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5214. Min Act: -0.1700

Data Index: 734314 (C4 (Web Text))

Max Activating Token Index: 500