Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1921 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.6744. Min Act: -0.1700

Data Index: 1342394 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.6119. Min Act: -0.1700

Data Index: 61921 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5494. Min Act: -0.1700

Data Index: 9187 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5494. Min Act: -0.1700

Data Index: 637125 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.6119. Min Act: -0.1700

Data Index: 860045 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5807. Min Act: -0.1700

Data Index: 201544 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5182. Min Act: -0.1700

Data Index: 171495 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5494. Min Act: -0.1700

Data Index: 843469 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.4869. Min Act: -0.1700

Data Index: 664588 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.4557. Min Act: -0.1700

Data Index: 1006664 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5182. Min Act: -0.1700

Data Index: 1054724 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.4557. Min Act: -0.1700

Data Index: 1105326 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5182. Min Act: -0.1700

Data Index: 575891 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5182. Min Act: -0.1700

Data Index: 1200529 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5182. Min Act: -0.1700

Data Index: 549214 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5182. Min Act: -0.1700

Data Index: 507324 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5494. Min Act: -0.1700

Data Index: 693904 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.5182. Min Act: -0.1700

Data Index: 774216 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.4869. Min Act: -0.1700

Data Index: 585044 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 5.6744. Min Range: -5.6744

Max Act: 5.4869. Min Act: -0.1700

Data Index: 18853 (C4 (Web Text))

Max Activating Token Index: 460