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

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

Neuron 1383 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: 5.8593. Min Range: -5.8593

Max Act: 5.8593. Min Act: -0.1700

Data Index: 560018 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.8281. Min Act: -0.1700

Data Index: 275902 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.7656. Min Act: -0.1700

Data Index: 376502 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.7343. Min Act: -0.1700

Data Index: 987970 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.7656. Min Act: -0.1700

Data Index: 1074187 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.7343. Min Act: -0.1700

Data Index: 1127698 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.6718. Min Act: -0.1700

Data Index: 1002930 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.6093. Min Act: -0.1700

Data Index: 418737 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5781. Min Act: -0.1700

Data Index: 180818 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5781. Min Act: -0.1700

Data Index: 785186 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5468. Min Act: -0.1700

Data Index: 870336 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5781. Min Act: -0.1700

Data Index: 988457 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.6406. Min Act: -0.1700

Data Index: 945172 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5781. Min Act: -0.1700

Data Index: 989724 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5468. Min Act: -0.1700

Data Index: 15793 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5468. Min Act: -0.1700

Data Index: 1005041 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5468. Min Act: -0.1700

Data Index: 959585 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5468. Min Act: -0.1700

Data Index: 615073 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5468. Min Act: -0.1700

Data Index: 956475 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 5.8593. Min Range: -5.8593

Max Act: 5.5468. Min Act: -0.1700

Data Index: 138405 (C4 (Web Text))

Max Activating Token Index: 255