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

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

Neuron 1471 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: 5.4801. Min Range: -5.4801

Max Act: 5.4801. Min Act: -0.1700

Data Index: 965591 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4801. Min Act: -0.1700

Data Index: 1200533 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4801. Min Act: -0.1699

Data Index: 798700 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4801. Min Act: -0.1700

Data Index: 1303080 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4489. Min Act: -0.1700

Data Index: 1353950 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3551. Min Act: -0.1700

Data Index: 1169840 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4176. Min Act: -0.1700

Data Index: 423215 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4489. Min Act: -0.1700

Data Index: 933560 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4176. Min Act: -0.1700

Data Index: 769785 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4489. Min Act: -0.1700

Data Index: 566776 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4176. Min Act: -0.1700

Data Index: 126477 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3551. Min Act: -0.1700

Data Index: 583275 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3864. Min Act: -0.1700

Data Index: 555953 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3864. Min Act: -0.1700

Data Index: 422923 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3864. Min Act: -0.1700

Data Index: 989378 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3864. Min Act: -0.1700

Data Index: 331537 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3864. Min Act: -0.1700

Data Index: 1060010 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3551. Min Act: -0.1700

Data Index: 271839 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.3551. Min Act: -0.1700

Data Index: 1062617 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 5.4801. Min Range: -5.4801

Max Act: 5.4176. Min Act: -0.1700

Data Index: 948954 (C4 (Web Text))

Max Activating Token Index: 665