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

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

Neuron 1433 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.8025. Min Act: -0.1700

Data Index: 518622 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.8025. Min Act: -0.1700

Data Index: 686488 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7712. Min Act: -0.1700

Data Index: 1281298 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7712. Min Act: -0.1700

Data Index: 122759 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7712. Min Act: -0.1700

Data Index: 55144 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7242. Min Act: -0.1700

Data Index: 1032457 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7399. Min Act: -0.1700

Data Index: 1284797 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7399. Min Act: -0.1700

Data Index: 1185118 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7242. Min Act: -0.1700

Data Index: 1296178 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7399. Min Act: -0.1700

Data Index: 444158 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.7399. Min Act: -0.1700

Data Index: 1179073 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.6930. Min Act: -0.1700

Data Index: 467786 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.6773. Min Act: -0.1700

Data Index: 845344 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.6460. Min Act: -0.1700

Data Index: 1101005 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.6147. Min Act: -0.1700

Data Index: 256629 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.6460. Min Act: -0.1700

Data Index: 1314376 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.5990. Min Act: -0.1700

Data Index: 724904 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.5677. Min Act: -0.1700

Data Index: 797978 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.5677. Min Act: -0.1700

Data Index: 788946 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.8025. Min Range: -3.8025

Max Act: 3.5677. Min Act: -0.1700

Data Index: 64717 (C4 (Web Text))

Max Activating Token Index: 352