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

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

Neuron 1698 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.3116. Min Act: -0.1700

Data Index: 1344094 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.3116. Min Act: -0.1700

Data Index: 300880 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2645. Min Act: -0.1700

Data Index: 172204 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2488. Min Act: -0.1700

Data Index: 1294266 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2645. Min Act: -0.1700

Data Index: 141797 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2488. Min Act: -0.1700

Data Index: 541333 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2173. Min Act: -0.1700

Data Index: 1314443 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2173. Min Act: -0.1700

Data Index: 1010925 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2488. Min Act: -0.1700

Data Index: 518382 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2016. Min Act: -0.1700

Data Index: 436363 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2173. Min Act: -0.1700

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2173. Min Act: -0.1700

Data Index: 1220821 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.1701. Min Act: -0.1700

Data Index: 321155 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.1858. Min Act: -0.1700

Data Index: 777392 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.1858. Min Act: -0.1700

Data Index: 457505 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.2016. Min Act: -0.1700

Data Index: 350755 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.1701. Min Act: -0.1700

Data Index: 377004 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.1858. Min Act: -0.1700

Data Index: 769824 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.1544. Min Act: -0.1700

Data Index: 1040107 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 3.3116. Min Range: -3.3116

Max Act: 3.1701. Min Act: -0.1700

Data Index: 27720 (C4 (Web Text))

Max Activating Token Index: 1013