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

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

Neuron 1216 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0780. Min Range: -3.0780

Max Act: 3.0780. Min Act: -0.1700

Data Index: 563173 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 3.0780. Min Range: -3.0780

Max Act: 3.0149. Min Act: -0.1700

Data Index: 1240057 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9991. Min Act: -0.1700

Data Index: 1152347 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9516. Min Act: -0.1700

Data Index: 200183 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9358. Min Act: -0.1700

Data Index: 604654 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9358. Min Act: -0.1700

Data Index: 1246469 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8723. Min Act: -0.1700

Data Index: 488677 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8723. Min Act: -0.1700

Data Index: 1467705 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8564. Min Act: -0.1700

Data Index: 497440 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8564. Min Act: -0.1700

Data Index: 949874 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8564. Min Act: -0.1700

Data Index: 523798 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8564. Min Act: -0.1700

Data Index: 720945 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8564. Min Act: -0.1700

Data Index: 679746 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8406. Min Act: -0.1700

Data Index: 360834 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8406. Min Act: -0.1700

Data Index: 141790 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8406. Min Act: -0.1700

Data Index: 166692 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8406. Min Act: -0.1700

Data Index: 333008 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8406. Min Act: -0.1700

Data Index: 79046 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8406. Min Act: -0.1700

Data Index: 769827 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8564. Min Act: -0.1700

Data Index: 444787 (C4 (Web Text))

Max Activating Token Index: 760