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

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

Neuron 1519 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.5133. Min Act: -0.1700

Data Index: 650789 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.5445. Min Act: -0.1700

Data Index: 53492 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.6070. Min Act: -0.1700

Data Index: 828925 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.5758. Min Act: -0.1699

Data Index: 423543 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.4508. Min Act: -0.1700

Data Index: 311825 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.4195. Min Act: -0.1700

Data Index: 122107 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.4508. Min Act: -0.1700

Data Index: 970328 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.3570. Min Act: -0.1700

Data Index: 986393 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.3883. Min Act: -0.1700

Data Index: 1173392 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.3258. Min Act: -0.1700

Data Index: 201845 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.3258. Min Act: -0.1700

Data Index: 1248912 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.2008. Min Act: -0.1700

Data Index: 679895 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.2008. Min Act: -0.1700

Data Index: 521119 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.2008. Min Act: -0.1700

Data Index: 1138316 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.2008. Min Act: -0.1700

Data Index: 1306886 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.1070. Min Act: -0.1700

Data Index: 894512 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.1695. Min Act: -0.1700

Data Index: 108806 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.1695. Min Act: -0.1700

Data Index: 1120210 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.1383. Min Act: -0.1700

Data Index: 913434 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 5.6070. Min Range: -5.6070

Max Act: 5.1383. Min Act: -0.1700

Data Index: 276742 (C4 (Web Text))

Max Activating Token Index: 812