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

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

Neuron 1068 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: 4.0253. Min Range: -4.0253

Max Act: 4.0253. Min Act: -0.1700

Data Index: 199012 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8690. Min Act: -0.1700

Data Index: 1059247 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8690. Min Act: -0.1700

Data Index: 985436 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8690. Min Act: -0.1700

Data Index: 68144 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8690. Min Act: -0.1700

Data Index: 132965 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8690. Min Act: -0.1700

Data Index: 853262 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8690. Min Act: -0.1700

Data Index: 1241931 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8064. Min Act: -0.1700

Data Index: 1277805 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8064. Min Act: -0.1700

Data Index: 1207080 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7439. Min Act: -0.1700

Data Index: 1386265 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7752. Min Act: -0.1700

Data Index: 584847 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.8064. Min Act: -0.1700

Data Index: 576465 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7752. Min Act: -0.1700

Data Index: 913749 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7126. Min Act: -0.1700

Data Index: 853792 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7439. Min Act: -0.1700

Data Index: 1224403 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.6813. Min Act: -0.1700

Data Index: 334610 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7439. Min Act: -0.1700

Data Index: 1100922 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7126. Min Act: -0.1700

Data Index: 296240 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7126. Min Act: -0.1700

Data Index: 1128504 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 4.0253. Min Range: -4.0253

Max Act: 3.7126. Min Act: -0.1700

Data Index: 270696 (C4 (Web Text))

Max Activating Token Index: 621