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

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

Neuron 517 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: 5.6620. Min Range: -5.6620

Max Act: 5.6620. Min Act: -0.1700

Data Index: 1082374 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.6308. Min Act: -0.1700

Data Index: 779836 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5995. Min Act: -0.1700

Data Index: 69309 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5995. Min Act: -0.1700

Data Index: 1341584 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5370. Min Act: -0.1700

Data Index: 356327 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4745. Min Act: -0.1700

Data Index: 890725 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4745. Min Act: -0.1700

Data Index: 1009552 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4120. Min Act: -0.1700

Data Index: 904208 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4433. Min Act: -0.1700

Data Index: 987208 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4745. Min Act: -0.1700

Data Index: 133940 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4433. Min Act: -0.1700

Data Index: 624409 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4433. Min Act: -0.1700

Data Index: 746407 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4433. Min Act: -0.1700

Data Index: 767880 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4120. Min Act: -0.1700

Data Index: 52845 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4745. Min Act: -0.1700

Data Index: 824990 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4745. Min Act: -0.1700

Data Index: 483520 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4433. Min Act: -0.1700

Data Index: 1333683 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4433. Min Act: -0.1700

Data Index: 941289 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.3808. Min Act: -0.1700

Data Index: 705018 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.3808. Min Act: -0.1700

Data Index: 265327 (C4 (Web Text))

Max Activating Token Index: 416