Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1832 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.8308. Min Act: -0.1700

Data Index: 1341857 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7682. Min Act: -0.1700

Data Index: 1296147 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7682. Min Act: -0.1700

Data Index: 38291 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7682. Min Act: -0.1700

Data Index: 322314 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7682. Min Act: -0.1700

Data Index: 356051 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7682. Min Act: -0.1700

Data Index: 1056478 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7057. Min Act: -0.1700

Data Index: 818492 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7370. Min Act: -0.1700

Data Index: 38495 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7057. Min Act: -0.1699

Data Index: 925581 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7057. Min Act: -0.1700

Data Index: 555150 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7057. Min Act: -0.1700

Data Index: 1179989 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7057. Min Act: -0.1700

Data Index: 712505 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.6744. Min Act: -0.1700

Data Index: 1176691 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.6744. Min Act: -0.1700

Data Index: 265805 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.6744. Min Act: -0.1700

Data Index: 557050 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.6744. Min Act: -0.1700

Data Index: 769560 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.6744. Min Act: -0.1700

Data Index: 1020880 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.6744. Min Act: -0.1700

Data Index: 957201 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.6744. Min Act: -0.1700

Data Index: 308307 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.6431. Min Act: -0.1700

Data Index: 288764 (C4 (Web Text))

Max Activating Token Index: 102