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

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

Neuron 1809 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.3157. Min Act: -0.1700

Data Index: 98732 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.2529. Min Act: -0.1699

Data Index: 650427 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.2529. Min Act: -0.1700

Data Index: 1305607 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.1900. Min Act: -0.1700

Data Index: 54642 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.2215. Min Act: -0.1699

Data Index: 532327 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.2215. Min Act: -0.1700

Data Index: 88620 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.2843. Min Act: -0.1700

Data Index: 275940 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.2215. Min Act: -0.1700

Data Index: 595814 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.1585. Min Act: -0.1697

Data Index: 188122 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.1900. Min Act: -0.1700

Data Index: 571779 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.2215. Min Act: -0.1699

Data Index: 239508 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.1585. Min Act: -0.1689

Data Index: 145017 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.1585. Min Act: -0.1700

Data Index: 550013 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.1270. Min Act: -0.1700

Data Index: 841983 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.0955. Min Act: -0.1700

Data Index: 214682 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.0639. Min Act: -0.1699

Data Index: 757187 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.1585. Min Act: -0.1700

Data Index: 231169 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.0955. Min Act: -0.1700

Data Index: 435382 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.1270. Min Act: -0.1700

Data Index: 218187 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 3.3157. Min Range: -3.3157

Max Act: 3.0955. Min Act: -0.1700

Data Index: 1405074 (Python Code)

Max Activating Token Index: 848