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

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

Neuron 799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.4919. Min Act: -0.1699

Data Index: 1260401 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.4919. Min Act: -0.1700

Data Index: 609781 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.2419. Min Act: -0.1700

Data Index: 1276997 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.4294. Min Act: -0.1700

Data Index: 1169037 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.3044. Min Act: -0.1700

Data Index: 281276 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.2419. Min Act: -0.1700

Data Index: 158872 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.2419. Min Act: -0.1700

Data Index: 364526 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.2419. Min Act: -0.1700

Data Index: 595214 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.1794. Min Act: -0.1700

Data Index: 572883 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.0857. Min Act: -0.1700

Data Index: 1331293 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.2419. Min Act: -0.1700

Data Index: 27775 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.2419. Min Act: -0.1700

Data Index: 938540 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.3669. Min Act: -0.1700

Data Index: 1246422 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.1482. Min Act: -0.1700

Data Index: 346377 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.2419. Min Act: -0.1700

Data Index: 756959 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.1794. Min Act: -0.1700

Data Index: 641006 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.2419. Min Act: -0.1700

Data Index: 311155 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.1794. Min Act: -0.1700

Data Index: 8712 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.1482. Min Act: -0.1700

Data Index: 610432 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 7.4919. Min Range: -7.4919

Max Act: 7.1794. Min Act: -0.1699

Data Index: 1202982 (C4 (Web Text))

Max Activating Token Index: 983