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

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

Neuron 1898 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: 5.7892. Min Range: -5.7892

Max Act: 5.7892. Min Act: -0.1700

Data Index: 613913 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.6955. Min Act: -0.1700

Data Index: 24843 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.6642. Min Act: -0.1700

Data Index: 1102864 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.5705. Min Act: -0.1700

Data Index: 248925 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.5705. Min Act: -0.1700

Data Index: 1055614 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.5392. Min Act: -0.1700

Data Index: 862777 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.5392. Min Act: -0.1700

Data Index: 104869 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.5392. Min Act: -0.1700

Data Index: 395385 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.4767. Min Act: -0.1700

Data Index: 790332 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.4767. Min Act: -0.1700

Data Index: 251011 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.4142. Min Act: -0.1700

Data Index: 881616 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.4142. Min Act: -0.1700

Data Index: 84999 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.4142. Min Act: -0.1700

Data Index: 149441 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.3830. Min Act: -0.1700

Data Index: 539238 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.3830. Min Act: -0.1700

Data Index: 861066 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.3517. Min Act: -0.1700

Data Index: 723620 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.3205. Min Act: -0.1700

Data Index: 55006 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.3830. Min Act: -0.1700

Data Index: 211198 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.3205. Min Act: -0.1700

Data Index: 279783 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 5.7892. Min Range: -5.7892

Max Act: 5.2892. Min Act: -0.1700

Data Index: 162580 (C4 (Web Text))

Max Activating Token Index: 400