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

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

Neuron 624 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: 5.2842. Min Range: -5.2842

Max Act: 5.1905. Min Act: -0.1700

Data Index: 223605 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 5.2842. Min Range: -5.2842

Max Act: 5.2842. Min Act: -0.1700

Data Index: 112534 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.9873. Min Act: -0.1700

Data Index: 129616 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.6905. Min Act: -0.1700

Data Index: 287492 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.6748. Min Act: -0.1700

Data Index: 461182 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.6905. Min Act: -0.1700

Data Index: 709140 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.5967. Min Act: -0.1700

Data Index: 749267 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.6592. Min Act: -0.1700

Data Index: 173602 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.6436. Min Act: -0.1700

Data Index: 293574 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.5967. Min Act: -0.1700

Data Index: 1061636 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.5811. Min Act: -0.1700

Data Index: 345978 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.7217. Min Act: -0.1700

Data Index: 713430 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.5342. Min Act: -0.1700

Data Index: 649746 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.5030. Min Act: -0.1700

Data Index: 272959 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.5186. Min Act: -0.1700

Data Index: 108793 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.5030. Min Act: -0.1700

Data Index: 629506 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.4717. Min Act: -0.1700

Data Index: 1258132 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.4561. Min Act: -0.1700

Data Index: 1258224 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.4248. Min Act: -0.1700

Data Index: 1251081 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.2842. Min Range: -5.2842

Max Act: 4.4561. Min Act: -0.1700

Data Index: 370129 (C4 (Web Text))

Max Activating Token Index: 213