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

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

Neuron 1930 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: 5.5807. Min Range: -5.5807

Max Act: 5.4244. Min Act: -0.1700

Data Index: 955292 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.5807. Min Act: -0.1700

Data Index: 1126061 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.5182. Min Act: -0.1700

Data Index: 959396 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.4244. Min Act: -0.1700

Data Index: 1050189 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.5182. Min Act: -0.1700

Data Index: 530520 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.4244. Min Act: -0.1700

Data Index: 1357017 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.4869. Min Act: -0.1700

Data Index: 109018 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.2994. Min Act: -0.1700

Data Index: 560982 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3619. Min Act: -0.1700

Data Index: 381922 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3307. Min Act: -0.1700

Data Index: 165515 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3619. Min Act: -0.1700

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.4557. Min Act: -0.1700

Data Index: 317104 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3307. Min Act: -0.1700

Data Index: 381747 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3307. Min Act: -0.1700

Data Index: 444579 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3619. Min Act: -0.1700

Data Index: 859940 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3619. Min Act: -0.1700

Data Index: 39597 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.2994. Min Act: -0.1700

Data Index: 853963 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3619. Min Act: -0.1699

Data Index: 423138 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.4244. Min Act: -0.1700

Data Index: 848420 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3619. Min Act: -0.1700

Data Index: 220458 (C4 (Web Text))

Max Activating Token Index: 880