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

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

Neuron 1626 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.9856. Min Act: -0.1700

Data Index: 107646 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.6102. Min Act: -0.1700

Data Index: 997152 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5789. Min Act: -0.1700

Data Index: 1015942 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.4849. Min Act: -0.1700

Data Index: 458199 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.4222. Min Act: -0.1700

Data Index: 955280 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.4065. Min Act: -0.1700

Data Index: 294822 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.4065. Min Act: -0.1700

Data Index: 505584 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.4535. Min Act: -0.1700

Data Index: 855076 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3908. Min Act: -0.1700

Data Index: 493789 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3751. Min Act: -0.1700

Data Index: 1104056 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3908. Min Act: -0.1700

Data Index: 539731 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3594. Min Act: -0.1700

Data Index: 711972 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3751. Min Act: -0.1700

Data Index: 252774 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3437. Min Act: -0.1700

Data Index: 1073013 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3594. Min Act: -0.1700

Data Index: 228204 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3594. Min Act: -0.1700

Data Index: 682570 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3594. Min Act: -0.1700

Data Index: 829542 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3594. Min Act: -0.1700

Data Index: 1289735 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3751. Min Act: -0.1700

Data Index: 1109228 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.3594. Min Act: -0.1700

Data Index: 459636 (C4 (Web Text))

Max Activating Token Index: 118