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

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

Neuron 1150 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: 4.2411. Min Range: -4.2411

Max Act: 4.2098. Min Act: -0.1700

Data Index: 166913 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.2411. Min Range: -4.2411

Max Act: 4.2411. Min Act: -0.1700

Data Index: 1164102 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 4.2411. Min Range: -4.2411

Max Act: 4.0222. Min Act: -0.1699

Data Index: 1253120 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.2411. Min Range: -4.2411

Max Act: 4.0848. Min Act: -0.1700

Data Index: 458056 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9910. Min Act: -0.1700

Data Index: 581660 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 4.2411. Min Range: -4.2411

Max Act: 4.0535. Min Act: -0.1700

Data Index: 892643 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9910. Min Act: -0.1700

Data Index: 110067 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9597. Min Act: -0.1700

Data Index: 702676 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9597. Min Act: -0.1700

Data Index: 1138312 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.8346. Min Act: -0.1700

Data Index: 1158925 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.8659. Min Act: -0.1700

Data Index: 70435 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9284. Min Act: -0.1700

Data Index: 534498 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9284. Min Act: -0.1700

Data Index: 1155527 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9910. Min Act: -0.1700

Data Index: 676844 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9284. Min Act: -0.1700

Data Index: 1065896 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.8659. Min Act: -0.1700

Data Index: 859537 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.9284. Min Act: -0.1700

Data Index: 610966 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.7095. Min Act: -0.1700

Data Index: 426493 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.8659. Min Act: -0.1700

Data Index: 208601 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 4.2411. Min Range: -4.2411

Max Act: 3.8346. Min Act: -0.1700

Data Index: 453423 (C4 (Web Text))

Max Activating Token Index: 432