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

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

Neuron 1569 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.7040. Min Act: -0.1700

Data Index: 895239 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6727. Min Act: -0.1700

Data Index: 268438 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6414. Min Act: -0.1700

Data Index: 785294 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6571. Min Act: -0.1700

Data Index: 317929 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6414. Min Act: -0.1700

Data Index: 1100593 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6258. Min Act: -0.1700

Data Index: 943017 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6571. Min Act: -0.1700

Data Index: 420263 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6258. Min Act: -0.1700

Data Index: 98169 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6414. Min Act: -0.1700

Data Index: 545309 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6414. Min Act: -0.1700

Data Index: 1279861 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6101. Min Act: -0.1700

Data Index: 434130 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6258. Min Act: -0.1700

Data Index: 674893 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6414. Min Act: -0.1700

Data Index: 499977 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6258. Min Act: -0.1700

Data Index: 742816 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6258. Min Act: -0.1700

Data Index: 319739 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6258. Min Act: -0.1700

Data Index: 468797 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6258. Min Act: -0.1700

Data Index: 146893 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6101. Min Act: -0.1700

Data Index: 105103 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6258. Min Act: -0.1700

Data Index: 786301 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6101. Min Act: -0.1700

Data Index: 1057904 (C4 (Web Text))

Max Activating Token Index: 707