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

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

Neuron 554 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.9851. Min Act: -0.1700

Data Index: 868910 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.9538. Min Act: -0.1700

Data Index: 109255 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.9538. Min Act: -0.1700

Data Index: 955080 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.8287. Min Act: -0.1700

Data Index: 856875 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.8600. Min Act: -0.1700

Data Index: 779905 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7975. Min Act: -0.1700

Data Index: 184870 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7975. Min Act: -0.1700

Data Index: 408705 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7975. Min Act: -0.1700

Data Index: 883796 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7975. Min Act: -0.1700

Data Index: 1068240 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.8287. Min Act: -0.1700

Data Index: 273372 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.8287. Min Act: -0.1700

Data Index: 1332062 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.8287. Min Act: -0.1700

Data Index: 804439 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7662. Min Act: -0.1700

Data Index: 615617 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7349. Min Act: -0.1700

Data Index: 1276067 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7662. Min Act: -0.1700

Data Index: 448942 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.8287. Min Act: -0.1700

Data Index: 946710 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.8287. Min Act: -0.1700

Data Index: 9397 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7975. Min Act: -0.1700

Data Index: 18464 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7975. Min Act: -0.1700

Data Index: 989183 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7662. Min Act: -0.1700

Data Index: 1025936 (C4 (Web Text))

Max Activating Token Index: 102