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

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

Neuron 1707 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: 3.5902. Min Range: -3.5902

Max Act: 3.5902. Min Act: -0.1700

Data Index: 336941 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.5902. Min Act: -0.1700

Data Index: 1096110 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.5589. Min Act: -0.1700

Data Index: 876949 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1202825 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.5119. Min Act: -0.1700

Data Index: 975805 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.5119. Min Act: -0.1700

Data Index: 809704 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4962. Min Act: -0.1700

Data Index: 600384 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4962. Min Act: -0.1700

Data Index: 503450 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4962. Min Act: -0.1700

Data Index: 1142343 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4649. Min Act: -0.1700

Data Index: 370832 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4649. Min Act: -0.1700

Data Index: 745848 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4492. Min Act: -0.1700

Data Index: 1046937 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4649. Min Act: -0.1700

Data Index: 1312649 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4492. Min Act: -0.1700

Data Index: 1216790 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4649. Min Act: -0.1700

Data Index: 1347149 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4335. Min Act: -0.1700

Data Index: 857766 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4335. Min Act: -0.1700

Data Index: 955340 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4492. Min Act: -0.1700

Data Index: 1185188 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4178. Min Act: -0.1700

Data Index: 940927 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 3.5902. Min Range: -3.5902

Max Act: 3.4335. Min Act: -0.1700

Data Index: 459694 (C4 (Web Text))

Max Activating Token Index: 685