Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 397 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.8318. Min Act: -0.1700

Data Index: 1142107 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.7067. Min Act: -0.1700

Data Index: 706210 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.6754. Min Act: -0.1700

Data Index: 440046 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.7067. Min Act: -0.1700

Data Index: 560209 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.7067. Min Act: -0.1700

Data Index: 1190480 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.6441. Min Act: -0.1700

Data Index: 938152 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.6441. Min Act: -0.1700

Data Index: 78522 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.6441. Min Act: -0.1700

Data Index: 881169 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.5188. Min Act: -0.1700

Data Index: 644 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.6441. Min Act: -0.1700

Data Index: 478481 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.5815. Min Act: -0.1700

Data Index: 754253 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.6128. Min Act: -0.1700

Data Index: 616209 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.5815. Min Act: -0.1700

Data Index: 1162554 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.6128. Min Act: -0.1700

Data Index: 880937 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.5815. Min Act: -0.1700

Data Index: 863547 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.5188. Min Act: -0.1700

Data Index: 1228575 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.5188. Min Act: -0.1700

Data Index: 383824 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.4248. Min Act: -0.1700

Data Index: 29958 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.5188. Min Act: -0.1700

Data Index: 977733 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 3.8318. Min Range: -3.8318

Max Act: 3.5501. Min Act: -0.1700

Data Index: 348709 (C4 (Web Text))

Max Activating Token Index: 390