Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1380 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.3310. Min Act: -0.1700

Data Index: 256477 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1581. Min Act: -0.1700

Data Index: 1276305 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1424. Min Act: -0.1700

Data Index: 610454 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1266. Min Act: -0.1700

Data Index: 928886 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1266. Min Act: -0.1700

Data Index: 1224113 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1424. Min Act: -0.1700

Data Index: 333458 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1108. Min Act: -0.1700

Data Index: 18936 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1266. Min Act: -0.1700

Data Index: 97171 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0951. Min Act: -0.1700

Data Index: 518062 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1424. Min Act: -0.1700

Data Index: 1064566 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0951. Min Act: -0.1700

Data Index: 1286400 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1108. Min Act: -0.1700

Data Index: 964817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.1108. Min Act: -0.1700

Data Index: 504857 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0951. Min Act: -0.1700

Data Index: 918686 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0793. Min Act: -0.1700

Data Index: 1006339 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0951. Min Act: -0.1700

Data Index: 313823 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0477. Min Act: -0.1700

Data Index: 135404 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0793. Min Act: -0.1700

Data Index: 776841 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0635. Min Act: -0.1700

Data Index: 539045 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 3.3310. Min Range: -3.3310

Max Act: 3.0477. Min Act: -0.1700

Data Index: 932065 (C4 (Web Text))

Max Activating Token Index: 823