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

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

Neuron 605 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: 9.9164. Min Range: -9.9164

Max Act: 9.9164. Min Act: -0.1700

Data Index: 1098900 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.8539. Min Act: -0.1700

Data Index: 384008 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.8539. Min Act: -0.1700

Data Index: 123776 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.6664. Min Act: -0.1700

Data Index: 735132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.6039. Min Act: -0.1700

Data Index: 1205105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.5414. Min Act: -0.1700

Data Index: 874667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.4164. Min Act: -0.1700

Data Index: 1099256 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.4164. Min Act: -0.1700

Data Index: 174796 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.4789. Min Act: -0.1700

Data Index: 345653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.3539. Min Act: -0.1700

Data Index: 765155 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.3539. Min Act: -0.1700

Data Index: 84583 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.2289. Min Act: -0.1700

Data Index: 1349290 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.2914. Min Act: -0.1700

Data Index: 1260446 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.4164. Min Act: -0.1700

Data Index: 1215915 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.2289. Min Act: -0.1700

Data Index: 728898 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.1664. Min Act: -0.1700

Data Index: 832361 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.2914. Min Act: -0.1700

Data Index: 486736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.0414. Min Act: -0.1700

Data Index: 337865 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.1039. Min Act: -0.1700

Data Index: 298184 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 9.9164. Min Range: -9.9164

Max Act: 9.1664. Min Act: -0.1700

Data Index: 764538 (C4 (Web Text))

Max Activating Token Index: 1023