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

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

Neuron 35 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: 3.5972. Min Range: -3.5972

Max Act: 3.5972. Min Act: -0.1700

Data Index: 442564 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5502. Min Act: -0.1700

Data Index: 469783 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5345. Min Act: -0.1700

Data Index: 1349661 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5032. Min Act: -0.1700

Data Index: 367722 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4719. Min Act: -0.1700

Data Index: 632112 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4092. Min Act: -0.1700

Data Index: 220060 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4092. Min Act: -0.1700

Data Index: 779231 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4248. Min Act: -0.1700

Data Index: 53902 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4248. Min Act: -0.1700

Data Index: 394159 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4092. Min Act: -0.1700

Data Index: 252194 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3935. Min Act: -0.1700

Data Index: 815360 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3935. Min Act: -0.1700

Data Index: 65674 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3778. Min Act: -0.1700

Data Index: 882601 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3935. Min Act: -0.1700

Data Index: 1192134 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3935. Min Act: -0.1700

Data Index: 880878 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3935. Min Act: -0.1700

Data Index: 678838 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3621. Min Act: -0.1700

Data Index: 814693 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3778. Min Act: -0.1700

Data Index: 460309 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3778. Min Act: -0.1700

Data Index: 490887 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.3778. Min Act: -0.1700

Data Index: 430760 (C4 (Web Text))

Max Activating Token Index: 38