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

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

Neuron 985 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.8739. Min Act: -0.1700

Data Index: 1200050 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.7801. Min Act: -0.1700

Data Index: 1227252 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.7801. Min Act: -0.1700

Data Index: 1156735 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.7488. Min Act: -0.1700

Data Index: 754209 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.7175. Min Act: -0.1700

Data Index: 1151041 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.6549. Min Act: -0.1700

Data Index: 812150 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.6862. Min Act: -0.1700

Data Index: 1054503 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.6862. Min Act: -0.1700

Data Index: 663587 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.6549. Min Act: -0.1700

Data Index: 43285 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5923. Min Act: -0.1700

Data Index: 1216852 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5923. Min Act: -0.1700

Data Index: 334161 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5923. Min Act: -0.1700

Data Index: 79776 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5610. Min Act: -0.1700

Data Index: 153184 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5923. Min Act: -0.1700

Data Index: 1147122 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5923. Min Act: -0.1700

Data Index: 685597 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5610. Min Act: -0.1700

Data Index: 496981 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5610. Min Act: -0.1700

Data Index: 136661 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5296. Min Act: -0.1700

Data Index: 199615 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5296. Min Act: -0.1700

Data Index: 437312 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 3.8739. Min Range: -3.8739

Max Act: 3.5296. Min Act: -0.1700

Data Index: 476314 (C4 (Web Text))

Max Activating Token Index: 950