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

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

Neuron 1475 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: 3.9023. Min Range: -3.9023

Max Act: 3.9023. Min Act: -0.1700

Data Index: 935261 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.9023. Min Act: -0.1700

Data Index: 1374135 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.8398. Min Act: -0.1700

Data Index: 504909 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.8398. Min Act: -0.1700

Data Index: 328288 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.8398. Min Act: -0.1700

Data Index: 962927 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7459. Min Act: -0.1700

Data Index: 1038860 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7459. Min Act: -0.1700

Data Index: 41874 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7459. Min Act: -0.1700

Data Index: 1175084 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7459. Min Act: -0.1700

Data Index: 770527 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7459. Min Act: -0.1700

Data Index: 455031 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7146. Min Act: -0.1700

Data Index: 225777 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7459. Min Act: -0.1700

Data Index: 721393 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7459. Min Act: -0.1700

Data Index: 1074449 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7772. Min Act: -0.1700

Data Index: 1106860 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7146. Min Act: -0.1700

Data Index: 687893 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.6833. Min Act: -0.1700

Data Index: 1651257 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7146. Min Act: -0.1700

Data Index: 1610848 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7146. Min Act: -0.1700

Data Index: 753767 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.7146. Min Act: -0.1700

Data Index: 929894 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 3.9023. Min Range: -3.9023

Max Act: 3.6833. Min Act: -0.1700

Data Index: 643297 (C4 (Web Text))

Max Activating Token Index: 812