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

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

Neuron 1929 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: 3.6430. Min Range: -3.6430

Max Act: 3.6430. Min Act: -0.1700

Data Index: 331965 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.5021. Min Act: -0.1700

Data Index: 807273 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.4550. Min Act: -0.1700

Data Index: 883269 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3609. Min Act: -0.1700

Data Index: 433563 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3766. Min Act: -0.1700

Data Index: 975668 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3609. Min Act: -0.1700

Data Index: 1017371 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3452. Min Act: -0.1700

Data Index: 115753 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3609. Min Act: -0.1700

Data Index: 742057 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3296. Min Act: -0.1700

Data Index: 53622 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3296. Min Act: -0.1700

Data Index: 526084 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3452. Min Act: -0.1700

Data Index: 1135784 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.2981. Min Act: -0.1700

Data Index: 1023200 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.2981. Min Act: -0.1700

Data Index: 82678 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3296. Min Act: -0.1700

Data Index: 916206 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3452. Min Act: -0.1700

Data Index: 854066 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.2981. Min Act: -0.1700

Data Index: 249295 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3139. Min Act: -0.1700

Data Index: 674660 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.2981. Min Act: -0.1700

Data Index: 1055069 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3296. Min Act: -0.1700

Data Index: 1275154 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 3.6430. Min Range: -3.6430

Max Act: 3.3139. Min Act: -0.1700

Data Index: 578308 (C4 (Web Text))

Max Activating Token Index: 758