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

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

Neuron 704 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: 5.3688. Min Range: -5.3688

Max Act: 5.3688. Min Act: -0.1700

Data Index: 242559 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.2438. Min Act: -0.1700

Data Index: 686627 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.1813. Min Act: -0.1700

Data Index: 276432 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.1813. Min Act: -0.1700

Data Index: 625883 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.1188. Min Act: -0.1700

Data Index: 500239 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.1188. Min Act: -0.1700

Data Index: 1259946 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0875. Min Act: -0.1700

Data Index: 471031 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.1813. Min Act: -0.1700

Data Index: 398722 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0875. Min Act: -0.1700

Data Index: 77435 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0250. Min Act: -0.1700

Data Index: 809910 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0875. Min Act: -0.1700

Data Index: 1263273 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0875. Min Act: -0.1700

Data Index: 971419 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0250. Min Act: -0.1700

Data Index: 949903 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0250. Min Act: -0.1700

Data Index: 422577 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0250. Min Act: -0.1700

Data Index: 433123 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0250. Min Act: -0.1700

Data Index: 411312 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0250. Min Act: -0.1700

Data Index: 800787 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 5.3688. Min Range: -5.3688

Max Act: 5.0563. Min Act: -0.1700

Data Index: 196220 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 5.3688. Min Range: -5.3688

Max Act: 4.9313. Min Act: -0.1700

Data Index: 312428 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.3688. Min Range: -5.3688

Max Act: 4.9313. Min Act: -0.1700

Data Index: 1075594 (C4 (Web Text))

Max Activating Token Index: 681