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

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

Neuron 544 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: 5.0688. Min Range: -5.0688

Max Act: 5.0688. Min Act: -0.1700

Data Index: 702558 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.9125. Min Act: -0.1700

Data Index: 85076 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.8188. Min Act: -0.1700

Data Index: 474519 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.8188. Min Act: -0.1700

Data Index: 43203 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.7250. Min Act: -0.1700

Data Index: 746669 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.7250. Min Act: -0.1700

Data Index: 889411 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.7875. Min Act: -0.1700

Data Index: 675713 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.7250. Min Act: -0.1700

Data Index: 41372 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.7250. Min Act: -0.1700

Data Index: 67251 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.6938. Min Act: -0.1700

Data Index: 1238655 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.6313. Min Act: -0.1700

Data Index: 337053 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.6938. Min Act: -0.1700

Data Index: 1147693 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.6938. Min Act: -0.1700

Data Index: 325563 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.6625. Min Act: -0.1700

Data Index: 1264388 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.6625. Min Act: -0.1700

Data Index: 884657 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.6938. Min Act: -0.1700

Data Index: 663929 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.5688. Min Act: -0.1700

Data Index: 113967 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.5375. Min Act: -0.1700

Data Index: 1035202 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.5375. Min Act: -0.1700

Data Index: 1102261 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 5.0688. Min Range: -5.0688

Max Act: 4.5375. Min Act: -0.1700

Data Index: 77033 (C4 (Web Text))

Max Activating Token Index: 732