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

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

Neuron 1023 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: 5.8275. Min Range: -5.8275

Max Act: 5.8275. Min Act: -0.1700

Data Index: 388103 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.8275. Min Act: -0.1700

Data Index: 1349482 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.7338. Min Act: -0.1700

Data Index: 851940 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.7650. Min Act: -0.1700

Data Index: 956882 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.7025. Min Act: -0.1700

Data Index: 516539 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.7338. Min Act: -0.1700

Data Index: 1185555 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.6713. Min Act: -0.1700

Data Index: 787595 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.6400. Min Act: -0.1700

Data Index: 1264544 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.6088. Min Act: -0.1700

Data Index: 1184869 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.6088. Min Act: -0.1700

Data Index: 430933 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5463. Min Act: -0.1700

Data Index: 1124403 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5463. Min Act: -0.1700

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5775. Min Act: -0.1700

Data Index: 177749 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5463. Min Act: -0.1700

Data Index: 1130233 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5150. Min Act: -0.1700

Data Index: 113532 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5775. Min Act: -0.1700

Data Index: 933738 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5150. Min Act: -0.1700

Data Index: 1195042 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5463. Min Act: -0.1700

Data Index: 301011 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5775. Min Act: -0.1700

Data Index: 597266 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 5.8275. Min Range: -5.8275

Max Act: 5.5463. Min Act: -0.1700

Data Index: 767272 (C4 (Web Text))

Max Activating Token Index: 849