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

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

Neuron 577 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: 5.9503. Min Range: -5.9503

Max Act: 5.9503. Min Act: -0.1700

Data Index: 1251505 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.8565. Min Act: -0.1700

Data Index: 868666 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.8565. Min Act: -0.1700

Data Index: 1183878 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.8565. Min Act: -0.1700

Data Index: 791173 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.8253. Min Act: -0.1700

Data Index: 891170 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.7628. Min Act: -0.1700

Data Index: 70710 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.7315. Min Act: -0.1700

Data Index: 5512 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.6065. Min Act: -0.1700

Data Index: 887300 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.7315. Min Act: -0.1700

Data Index: 1032908 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.5753. Min Act: -0.1700

Data Index: 880369 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.4659. Min Act: -0.1700

Data Index: 733973 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.5753. Min Act: -0.1700

Data Index: 463614 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.6378. Min Act: -0.1700

Data Index: 364737 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.5753. Min Act: -0.1700

Data Index: 72612 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.6690. Min Act: -0.1700

Data Index: 656030 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.5128. Min Act: -0.1700

Data Index: 334465 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.5753. Min Act: -0.1700

Data Index: 1099000 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.4971. Min Act: -0.1700

Data Index: 129761 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.4503. Min Act: -0.1700

Data Index: 487377 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 5.9503. Min Range: -5.9503

Max Act: 5.4346. Min Act: -0.1700

Data Index: 1004684 (C4 (Web Text))

Max Activating Token Index: 297