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

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

Neuron 450 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: 3.7845. Min Range: -3.7845

Max Act: 3.7845. Min Act: -0.1700

Data Index: 1347583 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.7532. Min Act: -0.1700

Data Index: 754996 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.7376. Min Act: -0.1700

Data Index: 902754 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.7532. Min Act: -0.1700

Data Index: 884017 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.6750. Min Act: -0.1700

Data Index: 141335 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.6907. Min Act: -0.1700

Data Index: 602445 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.6280. Min Act: -0.1700

Data Index: 666004 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5967. Min Act: -0.1700

Data Index: 174030 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5967. Min Act: -0.1700

Data Index: 1014850 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1313418 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.6124. Min Act: -0.1700

Data Index: 847554 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5811. Min Act: -0.1700

Data Index: 575248 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5811. Min Act: -0.1700

Data Index: 612328 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5498. Min Act: -0.1700

Data Index: 727762 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5498. Min Act: -0.1700

Data Index: 1196898 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5498. Min Act: -0.1700

Data Index: 476254 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5811. Min Act: -0.1700

Data Index: 508951 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5967. Min Act: -0.1700

Data Index: 110448 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5184. Min Act: -0.1700

Data Index: 493408 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5811. Min Act: -0.1700

Data Index: 31842 (C4 (Web Text))

Max Activating Token Index: 886