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

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

Neuron 1917 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: 5.5815. Min Range: -5.5815

Max Act: 5.5815. Min Act: -0.1700

Data Index: 146856 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.4878. Min Act: -0.1700

Data Index: 1328013 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.4878. Min Act: -0.1700

Data Index: 32226 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.3315. Min Act: -0.1700

Data Index: 128374 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.3628. Min Act: -0.1700

Data Index: 162412 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.3003. Min Act: -0.1700

Data Index: 1323364 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.3003. Min Act: -0.1700

Data Index: 458732 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.2065. Min Act: -0.1700

Data Index: 609204 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.2378. Min Act: -0.1700

Data Index: 591828 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.2378. Min Act: -0.1700

Data Index: 855653 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.2690. Min Act: -0.1700

Data Index: 1293621 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.2065. Min Act: -0.1700

Data Index: 163880 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.2690. Min Act: -0.1700

Data Index: 214799 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.1753. Min Act: -0.1700

Data Index: 90611 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.1753. Min Act: -0.1700

Data Index: 1295271 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.0503. Min Act: -0.1700

Data Index: 951308 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.1753. Min Act: -0.1700

Data Index: 421424 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.2065. Min Act: -0.1700

Data Index: 527519 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.2065. Min Act: -0.1700

Data Index: 1238349 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 5.5815. Min Range: -5.5815

Max Act: 5.1753. Min Act: -0.1700

Data Index: 650436 (C4 (Web Text))

Max Activating Token Index: 869