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

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

Neuron 1897 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: 3.2481. Min Range: -3.2481

Max Act: 3.2481. Min Act: -0.1700

Data Index: 73295 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2481. Min Act: -0.1700

Data Index: 449324 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2166. Min Act: -0.1700

Data Index: 1206130 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2481. Min Act: -0.1700

Data Index: 390550 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1149081 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2166. Min Act: -0.1700

Data Index: 1310600 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1273933 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2009. Min Act: -0.1700

Data Index: 40476 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2009. Min Act: -0.1700

Data Index: 577386 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1852. Min Act: -0.1700

Data Index: 717828 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1852. Min Act: -0.1700

Data Index: 212025 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.2009. Min Act: -0.1700

Data Index: 833201 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1852. Min Act: -0.1700

Data Index: 1125057 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1852. Min Act: -0.1700

Data Index: 663943 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1537. Min Act: -0.1700

Data Index: 1134793 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1852. Min Act: -0.1700

Data Index: 678414 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1537. Min Act: -0.1700

Data Index: 1287769 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1852. Min Act: -0.1700

Data Index: 1303912 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1694. Min Act: -0.1700

Data Index: 342920 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 3.2481. Min Range: -3.2481

Max Act: 3.1694. Min Act: -0.1700

Data Index: 349001 (C4 (Web Text))

Max Activating Token Index: 649