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

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

Neuron 26 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.5127. Min Act: -0.1700

Data Index: 1024913 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.3252. Min Act: -0.1700

Data Index: 859363 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.3252. Min Act: -0.1700

Data Index: 1213000 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.3252. Min Act: -0.1700

Data Index: 563474 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.2627. Min Act: -0.1700

Data Index: 772289 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.2627. Min Act: -0.1700

Data Index: 320590 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1377. Min Act: -0.1700

Data Index: 390991 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.2002. Min Act: -0.1700

Data Index: 404294 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1689. Min Act: -0.1700

Data Index: 129652 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1377. Min Act: -0.1700

Data Index: 439080 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1689. Min Act: -0.1700

Data Index: 596535 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.2002. Min Act: -0.1700

Data Index: 1356389 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.2002. Min Act: -0.1700

Data Index: 1210283 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1377. Min Act: -0.1700

Data Index: 1244851 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1377. Min Act: -0.1700

Data Index: 285167 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1064. Min Act: -0.1700

Data Index: 952512 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1064. Min Act: -0.1700

Data Index: 831543 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.1064. Min Act: -0.1700

Data Index: 1351292 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.0752. Min Act: -0.1700

Data Index: 341416 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 5.5127. Min Range: -5.5127

Max Act: 5.0752. Min Act: -0.1700

Data Index: 90799 (C4 (Web Text))

Max Activating Token Index: 491