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

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

Neuron 273 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.5278. Min Act: -0.1700

Data Index: 471318 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.4651. Min Act: -0.1700

Data Index: 773076 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3710. Min Act: -0.1700

Data Index: 167259 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.4024. Min Act: -0.1700

Data Index: 15519 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3867. Min Act: -0.1700

Data Index: 1025304 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3553. Min Act: -0.1700

Data Index: 156254 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3239. Min Act: -0.1700

Data Index: 724828 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.3396. Min Act: -0.1700

Data Index: 1278970 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2925. Min Act: -0.1700

Data Index: 201015 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2925. Min Act: -0.1700

Data Index: 732012 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1119961 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2611. Min Act: -0.1700

Data Index: 111534 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2454. Min Act: -0.1700

Data Index: 1183948 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.1982. Min Act: -0.1700

Data Index: 848269 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2454. Min Act: -0.1700

Data Index: 1189508 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2611. Min Act: -0.1700

Data Index: 593854 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2296. Min Act: -0.1700

Data Index: 240858 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.1824. Min Act: -0.1700

Data Index: 793643 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2139. Min Act: -0.1700

Data Index: 184105 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.5278. Min Range: -3.5278

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1333252 (C4 (Web Text))

Max Activating Token Index: 793