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

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

Neuron 347 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: 3.8655. Min Range: -3.8655

Max Act: 3.8655. Min Act: -0.1700

Data Index: 220350 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7717. Min Act: -0.1700

Data Index: 224265 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7091. Min Act: -0.1700

Data Index: 375603 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7091. Min Act: -0.1700

Data Index: 57317 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7091. Min Act: -0.1700

Data Index: 1168957 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6778. Min Act: -0.1700

Data Index: 1131932 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6778. Min Act: -0.1700

Data Index: 1245780 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6152. Min Act: -0.1700

Data Index: 261116 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6152. Min Act: -0.1700

Data Index: 870678 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6152. Min Act: -0.1700

Data Index: 1043033 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6778. Min Act: -0.1700

Data Index: 496871 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.5526. Min Act: -0.1700

Data Index: 1165311 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.5839. Min Act: -0.1700

Data Index: 534231 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6152. Min Act: -0.1700

Data Index: 405583 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.5839. Min Act: -0.1700

Data Index: 249738 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6152. Min Act: -0.1700

Data Index: 802217 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6465. Min Act: -0.1700

Data Index: 327223 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6152. Min Act: -0.1700

Data Index: 307130 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6152. Min Act: -0.1700

Data Index: 708920 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6465. Min Act: -0.1700

Data Index: 564151 (C4 (Web Text))

Max Activating Token Index: 367