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

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

Neuron 738 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.9008. Min Act: -0.1700

Data Index: 398850 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.8695. Min Act: -0.1700

Data Index: 1226531 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.8382. Min Act: -0.1700

Data Index: 1081806 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.8069. Min Act: -0.1700

Data Index: 976119 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.8069. Min Act: -0.1700

Data Index: 320532 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.8695. Min Act: -0.1700

Data Index: 971953 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7757. Min Act: -0.1700

Data Index: 654406 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7444. Min Act: -0.1700

Data Index: 1167874 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7757. Min Act: -0.1700

Data Index: 953395 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7444. Min Act: -0.1700

Data Index: 122359 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7444. Min Act: -0.1700

Data Index: 55878 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7131. Min Act: -0.1700

Data Index: 1281612 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7444. Min Act: -0.1700

Data Index: 1252440 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7444. Min Act: -0.1700

Data Index: 1037674 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7131. Min Act: -0.1700

Data Index: 788133 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7131. Min Act: -0.1700

Data Index: 1045808 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7131. Min Act: -0.1700

Data Index: 1198158 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7131. Min Act: -0.1700

Data Index: 238619 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7444. Min Act: -0.1700

Data Index: 785664 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 3.9008. Min Range: -3.9008

Max Act: 3.7444. Min Act: -0.1700

Data Index: 1117293 (C4 (Web Text))

Max Activating Token Index: 690