Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 128 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.2040. Min Act: -0.1700

Data Index: 855577 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.2977. Min Act: -0.1700

Data Index: 166434 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.0790. Min Act: -0.1700

Data Index: 921894 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.1415. Min Act: -0.1700

Data Index: 1274801 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.0790. Min Act: -0.1700

Data Index: 1290098 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.1415. Min Act: -0.1700

Data Index: 647415 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.0790. Min Act: -0.1700

Data Index: 1350744 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9540. Min Act: -0.1700

Data Index: 987174 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9540. Min Act: -0.1700

Data Index: 1059095 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9852. Min Act: -0.1700

Data Index: 409716 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9852. Min Act: -0.1700

Data Index: 660617 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.2352. Min Act: -0.1700

Data Index: 1081795 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.1102. Min Act: -0.1700

Data Index: 191782 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9852. Min Act: -0.1700

Data Index: 1238430 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.8915. Min Act: -0.1700

Data Index: 804972 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9227. Min Act: -0.1700

Data Index: 1209836 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9540. Min Act: -0.1700

Data Index: 436740 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 5.2977. Min Range: -5.2977

Max Act: 5.0477. Min Act: -0.1700

Data Index: 204450 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9227. Min Act: -0.1700

Data Index: 778886 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 5.2977. Min Range: -5.2977

Max Act: 4.9227. Min Act: -0.1700

Data Index: 1016288 (C4 (Web Text))

Max Activating Token Index: 713