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

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

Neuron 1093 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: 5.3932. Min Range: -5.3932

Max Act: 5.3620. Min Act: -0.1699

Data Index: 645485 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.3932. Min Act: -0.1700

Data Index: 1160946 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.2995. Min Act: -0.1700

Data Index: 850698 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.2370. Min Act: -0.1700

Data Index: 224511 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.2057. Min Act: -0.1700

Data Index: 611163 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.2370. Min Act: -0.1700

Data Index: 732295 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.2370. Min Act: -0.1700

Data Index: 440781 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1745. Min Act: -0.1700

Data Index: 496801 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1745. Min Act: -0.1700

Data Index: 372422 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1745. Min Act: -0.1700

Data Index: 1133483 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1432. Min Act: -0.1700

Data Index: 782151 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1432. Min Act: -0.1699

Data Index: 1029160 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1432. Min Act: -0.1700

Data Index: 730190 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1120. Min Act: -0.1699

Data Index: 241384 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1120. Min Act: -0.1700

Data Index: 698776 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1120. Min Act: -0.1700

Data Index: 842396 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1745. Min Act: -0.1698

Data Index: 1052848 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1745. Min Act: -0.1700

Data Index: 214189 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1432. Min Act: -0.1700

Data Index: 539003 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 5.3932. Min Range: -5.3932

Max Act: 5.1432. Min Act: -0.1700

Data Index: 687880 (C4 (Web Text))

Max Activating Token Index: 49