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

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

Neuron 1417 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1872. Min Range: -5.1872

Max Act: 5.1872. Min Act: -0.1700

Data Index: 1118535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.1872. Min Range: -5.1872

Max Act: 5.0935. Min Act: -0.1700

Data Index: 775327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.1872. Min Range: -5.1872

Max Act: 5.0935. Min Act: -0.1700

Data Index: 85810 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.9685. Min Act: -0.1700

Data Index: 484832 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.9060. Min Act: -0.1700

Data Index: 734823 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.9997. Min Act: -0.1700

Data Index: 43851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.9685. Min Act: -0.1700

Data Index: 733633 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.9060. Min Act: -0.1700

Data Index: 1112948 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.9685. Min Act: -0.1700

Data Index: 412104 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.9060. Min Act: -0.1700

Data Index: 181413 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.8122. Min Act: -0.1700

Data Index: 808983 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.7810. Min Act: -0.1700

Data Index: 346742 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.7497. Min Act: -0.1700

Data Index: 893289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.6872. Min Act: -0.1700

Data Index: 520962 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.7497. Min Act: -0.1700

Data Index: 88612 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.7185. Min Act: -0.1700

Data Index: 279136 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.6872. Min Act: -0.1700

Data Index: 320348 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.7185. Min Act: -0.1700

Data Index: 400388 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.7185. Min Act: -0.1700

Data Index: 266119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.1872. Min Range: -5.1872

Max Act: 4.6872. Min Act: -0.1700

Data Index: 768975 (C4 (Web Text))

Max Activating Token Index: 1023