Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1829 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1334669 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.7763. Min Act: -0.1700

Data Index: 726966 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.7294. Min Act: -0.1700

Data Index: 922934 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.6355. Min Act: -0.1700

Data Index: 922568 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.6041. Min Act: -0.1700

Data Index: 1162754 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.6355. Min Act: -0.1700

Data Index: 1120332 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5728. Min Act: -0.1700

Data Index: 493470 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5415. Min Act: -0.1700

Data Index: 325225 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1185586 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5728. Min Act: -0.1700

Data Index: 1024477 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1205436 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5572. Min Act: -0.1700

Data Index: 972463 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1158293 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5258. Min Act: -0.1700

Data Index: 73298 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5572. Min Act: -0.1700

Data Index: 69949 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1071468 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5258. Min Act: -0.1700

Data Index: 882585 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5258. Min Act: -0.1700

Data Index: 124950 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.4788. Min Act: -0.1700

Data Index: 946095 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 3.9170. Min Range: -3.9170

Max Act: 3.5258. Min Act: -0.1700

Data Index: 1213536 (C4 (Web Text))

Max Activating Token Index: 510