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

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

Neuron 1541 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: 5.2358. Min Range: -5.2358

Max Act: 5.2358. Min Act: -0.1700

Data Index: 191454 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.2046. Min Act: -0.1700

Data Index: 549093 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.1733. Min Act: -0.1700

Data Index: 838512 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.1733. Min Act: -0.1700

Data Index: 210460 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.1108. Min Act: -0.1700

Data Index: 718517 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.1108. Min Act: -0.1700

Data Index: 889518 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.0796. Min Act: -0.1700

Data Index: 138260 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.0483. Min Act: -0.1700

Data Index: 185112 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.0171. Min Act: -0.1700

Data Index: 1251269 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.0483. Min Act: -0.1700

Data Index: 636369 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.0483. Min Act: -0.1700

Data Index: 528254 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 5.2358. Min Range: -5.2358

Max Act: 4.9546. Min Act: -0.1700

Data Index: 490997 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.0171. Min Act: -0.1700

Data Index: 1213202 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 5.2358. Min Range: -5.2358

Max Act: 4.9858. Min Act: -0.1700

Data Index: 653721 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 5.2358. Min Range: -5.2358

Max Act: 5.0171. Min Act: -0.1700

Data Index: 1348249 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 5.2358. Min Range: -5.2358

Max Act: 4.9858. Min Act: -0.1700

Data Index: 217380 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 5.2358. Min Range: -5.2358

Max Act: 4.9233. Min Act: -0.1700

Data Index: 1238623 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 5.2358. Min Range: -5.2358

Max Act: 4.9233. Min Act: -0.1700

Data Index: 801809 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 5.2358. Min Range: -5.2358

Max Act: 4.9858. Min Act: -0.1700

Data Index: 93150 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 5.2358. Min Range: -5.2358

Max Act: 4.9546. Min Act: -0.1700

Data Index: 1142701 (C4 (Web Text))

Max Activating Token Index: 757