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

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

Neuron 1894 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1875. Min Range: -3.1875

Max Act: 3.1875. Min Act: -0.1700

Data Index: 517361 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 3.1875. Min Range: -3.1875

Max Act: 3.1245. Min Act: -0.1700

Data Index: 20617 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 3.1875. Min Range: -3.1875

Max Act: 3.1245. Min Act: -0.1700

Data Index: 757896 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 3.1875. Min Range: -3.1875

Max Act: 3.0140. Min Act: -0.1700

Data Index: 423702 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 3.1875. Min Range: -3.1875

Max Act: 3.0140. Min Act: -0.1700

Data Index: 1192060 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8715. Min Act: -0.1700

Data Index: 1073838 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8079. Min Act: -0.1700

Data Index: 138409 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7760. Min Act: -0.1700

Data Index: 1292533 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7920. Min Act: -0.1700

Data Index: 318429 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7760. Min Act: -0.1700

Data Index: 665736 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7601. Min Act: -0.1700

Data Index: 737974 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7441. Min Act: -0.1700

Data Index: 1071596 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7281. Min Act: -0.1700

Data Index: 675664 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7441. Min Act: -0.1700

Data Index: 550679 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7441. Min Act: -0.1700

Data Index: 239928 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7601. Min Act: -0.1700

Data Index: 260949 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7281. Min Act: -0.1700

Data Index: 376763 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7441. Min Act: -0.1700

Data Index: 723880 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7281. Min Act: -0.1700

Data Index: 532920 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.7281. Min Act: -0.1700

Data Index: 357193 (C4 (Web Text))

Max Activating Token Index: 970