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

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

Neuron 1441 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: 3.4398. Min Range: -3.4398

Max Act: 3.4398. Min Act: -0.1700

Data Index: 874131 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3614. Min Act: -0.1700

Data Index: 8150 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3614. Min Act: -0.1700

Data Index: 1206869 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3300. Min Act: -0.1700

Data Index: 1083759 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3614. Min Act: -0.1700

Data Index: 586625 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2829. Min Act: -0.1700

Data Index: 808548 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2986. Min Act: -0.1700

Data Index: 581068 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2672. Min Act: -0.1700

Data Index: 335511 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2672. Min Act: -0.1700

Data Index: 1354102 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2672. Min Act: -0.1700

Data Index: 275176 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2672. Min Act: -0.1700

Data Index: 160408 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2672. Min Act: -0.1700

Data Index: 1073315 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2672. Min Act: -0.1700

Data Index: 1101906 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2200. Min Act: -0.1700

Data Index: 145797 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2358. Min Act: -0.1700

Data Index: 162778 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2200. Min Act: -0.1700

Data Index: 1031594 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.1886. Min Act: -0.1700

Data Index: 1322184 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2043. Min Act: -0.1700

Data Index: 879360 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2043. Min Act: -0.1700

Data Index: 249420 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.1886. Min Act: -0.1700

Data Index: 24160 (C4 (Web Text))

Max Activating Token Index: 264