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

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

Neuron 1977 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: 3.8619. Min Range: -3.8619

Max Act: 3.8619. Min Act: -0.1700

Data Index: 706892 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.8307. Min Act: -0.1700

Data Index: 3613 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6742. Min Act: -0.1700

Data Index: 1003506 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.7368. Min Act: -0.1700

Data Index: 938193 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.7212. Min Act: -0.1700

Data Index: 763021 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6742. Min Act: -0.1700

Data Index: 935971 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6116. Min Act: -0.1700

Data Index: 1041185 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6742. Min Act: -0.1700

Data Index: 331788 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6429. Min Act: -0.1700

Data Index: 449379 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.7055. Min Act: -0.1700

Data Index: 1105503 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6586. Min Act: -0.1700

Data Index: 303894 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6586. Min Act: -0.1700

Data Index: 410802 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6429. Min Act: -0.1700

Data Index: 370050 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6742. Min Act: -0.1700

Data Index: 944680 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6116. Min Act: -0.1700

Data Index: 217296 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6116. Min Act: -0.1700

Data Index: 649373 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6273. Min Act: -0.1700

Data Index: 425996 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5803. Min Act: -0.1700

Data Index: 248093 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5959. Min Act: -0.1700

Data Index: 198916 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5646. Min Act: -0.1700

Data Index: 951613 (C4 (Web Text))

Max Activating Token Index: 344