Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 73 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.5841. Min Act: -0.1700

Data Index: 13837 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.5528. Min Act: -0.1700

Data Index: 422747 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.4278. Min Act: -0.1700

Data Index: 465160 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.4591. Min Act: -0.1700

Data Index: 805340 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.4591. Min Act: -0.1700

Data Index: 573207 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.4278. Min Act: -0.1700

Data Index: 848021 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3653. Min Act: -0.1700

Data Index: 144569 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3028. Min Act: -0.1700

Data Index: 963435 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3028. Min Act: -0.1700

Data Index: 1051200 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3966. Min Act: -0.1700

Data Index: 922569 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3341. Min Act: -0.1700

Data Index: 1028393 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3028. Min Act: -0.1700

Data Index: 618847 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3028. Min Act: -0.1700

Data Index: 1004952 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3028. Min Act: -0.1700

Data Index: 646365 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.3341. Min Act: -0.1700

Data Index: 291054 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.2091. Min Act: -0.1700

Data Index: 434830 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.2716. Min Act: -0.1700

Data Index: 934967 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.2716. Min Act: -0.1700

Data Index: 797988 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.2403. Min Act: -0.1700

Data Index: 289286 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 5.5841. Min Range: -5.5841

Max Act: 5.2091. Min Act: -0.1700

Data Index: 302707 (C4 (Web Text))

Max Activating Token Index: 1004