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

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

Neuron 51 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: 4.2556. Min Range: -4.2556

Max Act: 4.2556. Min Act: -0.1700

Data Index: 1308201 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 4.2556. Min Range: -4.2556

Max Act: 4.2244. Min Act: -0.1700

Data Index: 1038776 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 4.2556. Min Range: -4.2556

Max Act: 4.1306. Min Act: -0.1700

Data Index: 1541567 (Python Code)

Max Activating Token Index: 243

Text #3

Max Range: 4.2556. Min Range: -4.2556

Max Act: 4.1619. Min Act: -0.1700

Data Index: 369678 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 4.2556. Min Range: -4.2556

Max Act: 4.0681. Min Act: -0.1700

Data Index: 658278 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 4.2556. Min Range: -4.2556

Max Act: 4.0524. Min Act: -0.1700

Data Index: 529818 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 4.2556. Min Range: -4.2556

Max Act: 4.0524. Min Act: -0.1700

Data Index: 871854 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 4.2556. Min Range: -4.2556

Max Act: 4.0212. Min Act: -0.1700

Data Index: 1280510 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9899. Min Act: -0.1700

Data Index: 1048904 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9899. Min Act: -0.1700

Data Index: 834178 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9743. Min Act: -0.1700

Data Index: 419409 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9743. Min Act: -0.1700

Data Index: 82720 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9430. Min Act: -0.1700

Data Index: 967454 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9586. Min Act: -0.1700

Data Index: 681646 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9117. Min Act: -0.1700

Data Index: 766335 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9586. Min Act: -0.1700

Data Index: 1149077 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9274. Min Act: -0.1700

Data Index: 739497 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9274. Min Act: -0.1700

Data Index: 928324 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9274. Min Act: -0.1700

Data Index: 317549 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 4.2556. Min Range: -4.2556

Max Act: 3.9274. Min Act: -0.1700

Data Index: 1051407 (C4 (Web Text))

Max Activating Token Index: 449