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

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

Neuron 446 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: 3.7996. Min Range: -3.7996

Max Act: 3.7996. Min Act: -0.1700

Data Index: 59600 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7840. Min Act: -0.1700

Data Index: 1102313 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7840. Min Act: -0.1700

Data Index: 78649 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7840. Min Act: -0.1700

Data Index: 45949 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7527. Min Act: -0.1700

Data Index: 290343 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7527. Min Act: -0.1700

Data Index: 494311 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7370. Min Act: -0.1700

Data Index: 1324999 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7370. Min Act: -0.1700

Data Index: 714947 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.6901. Min Act: -0.1700

Data Index: 646080 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.6588. Min Act: -0.1700

Data Index: 1267984 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7057. Min Act: -0.1700

Data Index: 60077 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.6744. Min Act: -0.1700

Data Index: 311021 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7057. Min Act: -0.1700

Data Index: 308138 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.6744. Min Act: -0.1700

Data Index: 1301313 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7057. Min Act: -0.1700

Data Index: 952533 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7057. Min Act: -0.1700

Data Index: 1285008 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.6588. Min Act: -0.1700

Data Index: 2143 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.7057. Min Act: -0.1700

Data Index: 861820 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.6744. Min Act: -0.1700

Data Index: 845456 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 3.7996. Min Range: -3.7996

Max Act: 3.6901. Min Act: -0.1700

Data Index: 1111943 (C4 (Web Text))

Max Activating Token Index: 769