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

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

Neuron 161 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: 3.1035. Min Range: -3.1035

Max Act: 3.1035. Min Act: -0.1700

Data Index: 564670 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1035. Min Range: -3.1035

Max Act: 3.0877. Min Act: -0.1700

Data Index: 1059915 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.1035. Min Range: -3.1035

Max Act: 3.0246. Min Act: -0.1700

Data Index: 1239669 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.1035. Min Range: -3.1035

Max Act: 3.0561. Min Act: -0.1700

Data Index: 616398 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.1035. Min Range: -3.1035

Max Act: 3.0246. Min Act: -0.1700

Data Index: 707256 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.1035. Min Range: -3.1035

Max Act: 3.0404. Min Act: -0.1700

Data Index: 192945 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.1035. Min Range: -3.1035

Max Act: 3.0088. Min Act: -0.1700

Data Index: 699494 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9929. Min Act: -0.1700

Data Index: 1197619 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9929. Min Act: -0.1700

Data Index: 342452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9771. Min Act: -0.1700

Data Index: 702039 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9613. Min Act: -0.1700

Data Index: 935880 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9929. Min Act: -0.1700

Data Index: 256463 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9455. Min Act: -0.1700

Data Index: 1322383 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9613. Min Act: -0.1700

Data Index: 1025648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9613. Min Act: -0.1700

Data Index: 918021 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9771. Min Act: -0.1700

Data Index: 612499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9455. Min Act: -0.1700

Data Index: 325177 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9455. Min Act: -0.1700

Data Index: 1178110 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9613. Min Act: -0.1700

Data Index: 895489 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9296. Min Act: -0.1700

Data Index: 1043269 (C4 (Web Text))

Max Activating Token Index: 1023