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

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

Neuron 760 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0757. Min Range: -3.0757

Max Act: 3.0757. Min Act: -0.1700

Data Index: 678434 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 3.0757. Min Range: -3.0757

Max Act: 3.0600. Min Act: -0.1700

Data Index: 304252 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.0757. Min Range: -3.0757

Max Act: 3.0757. Min Act: -0.1700

Data Index: 298539 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 3.0757. Min Range: -3.0757

Max Act: 3.0757. Min Act: -0.1700

Data Index: 659847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.0757. Min Range: -3.0757

Max Act: 3.0126. Min Act: -0.1700

Data Index: 1200552 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 3.0757. Min Range: -3.0757

Max Act: 3.0284. Min Act: -0.1700

Data Index: 171569 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 3.0757. Min Range: -3.0757

Max Act: 3.0126. Min Act: -0.1700

Data Index: 955652 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 3.0757. Min Range: -3.0757

Max Act: 3.0126. Min Act: -0.1700

Data Index: 113683 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9810. Min Act: -0.1700

Data Index: 948002 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9968. Min Act: -0.1700

Data Index: 133001 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9968. Min Act: -0.1700

Data Index: 976912 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9968. Min Act: -0.1700

Data Index: 913995 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9968. Min Act: -0.1700

Data Index: 20224 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9810. Min Act: -0.1700

Data Index: 265753 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9810. Min Act: -0.1700

Data Index: 711517 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9651. Min Act: -0.1700

Data Index: 1059048 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9651. Min Act: -0.1700

Data Index: 311216 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9651. Min Act: -0.1700

Data Index: 628869 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9810. Min Act: -0.1700

Data Index: 323257 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.0757. Min Range: -3.0757

Max Act: 2.9651. Min Act: -0.1700

Data Index: 922567 (C4 (Web Text))

Max Activating Token Index: 803