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

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

Neuron 961 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.2192. Min Act: -0.1700

Data Index: 368884 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.2192. Min Act: -0.1700

Data Index: 802161 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.2192. Min Act: -0.1700

Data Index: 1045714 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.2035. Min Act: -0.1700

Data Index: 1254520 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.2035. Min Act: -0.1700

Data Index: 1257015 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.2035. Min Act: -0.1700

Data Index: 1084686 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1877. Min Act: -0.1700

Data Index: 1280862 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1877. Min Act: -0.1700

Data Index: 1271338 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1877. Min Act: -0.1700

Data Index: 931229 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1720. Min Act: -0.1700

Data Index: 796347 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1720. Min Act: -0.1700

Data Index: 1331948 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1720. Min Act: -0.1700

Data Index: 966104 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1570694 (Python Code)

Max Activating Token Index: 154

Text #13

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1238470 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1563. Min Act: -0.1700

Data Index: 486846 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1563. Min Act: -0.1700

Data Index: 139590 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1405. Min Act: -0.1700

Data Index: 762238 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1720. Min Act: -0.1700

Data Index: 604769 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1720. Min Act: -0.1700

Data Index: 658301 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1248. Min Act: -0.1700

Data Index: 162055 (C4 (Web Text))

Max Activating Token Index: 198