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

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

Neuron 183 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: 7.9778. Min Range: -7.9778

Max Act: 7.9778. Min Act: -0.1699

Data Index: 440885 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.9153. Min Act: -0.1700

Data Index: 887024 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.7903. Min Act: -0.1700

Data Index: 854237 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.6028. Min Act: -0.1700

Data Index: 985046 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.6028. Min Act: -0.1700

Data Index: 668339 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.6028. Min Act: -0.1700

Data Index: 155000 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.6028. Min Act: -0.1700

Data Index: 146377 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.6028. Min Act: -0.1700

Data Index: 452702 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4778. Min Act: -0.1700

Data Index: 831768 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4778. Min Act: -0.1700

Data Index: 728945 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.5403. Min Act: -0.1700

Data Index: 390863 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4778. Min Act: -0.1700

Data Index: 1347700 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4778. Min Act: -0.1700

Data Index: 1073720 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4153. Min Act: -0.1700

Data Index: 1131068 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4778. Min Act: -0.1700

Data Index: 1148875 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4778. Min Act: -0.1700

Data Index: 102190 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4778. Min Act: -0.1700

Data Index: 422407 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4778. Min Act: -0.1700

Data Index: 1265870 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4153. Min Act: -0.1700

Data Index: 138543 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 7.9778. Min Range: -7.9778

Max Act: 7.4153. Min Act: -0.1700

Data Index: 893281 (C4 (Web Text))

Max Activating Token Index: 86