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

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

Neuron 1663 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0649. Min Range: -4.0649

Max Act: 4.0649. Min Act: -0.1700

Data Index: 90242 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.9711. Min Act: -0.1700

Data Index: 605113 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.9398. Min Act: -0.1700

Data Index: 790903 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.9398. Min Act: -0.1700

Data Index: 799787 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.9086. Min Act: -0.1700

Data Index: 301336 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.9711. Min Act: -0.1700

Data Index: 196940 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8773. Min Act: -0.1700

Data Index: 292576 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8773. Min Act: -0.1700

Data Index: 513752 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.9398. Min Act: -0.1700

Data Index: 289650 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.9086. Min Act: -0.1700

Data Index: 517515 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8147. Min Act: -0.1700

Data Index: 772958 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8773. Min Act: -0.1700

Data Index: 119345 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8147. Min Act: -0.1700

Data Index: 922952 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8773. Min Act: -0.1700

Data Index: 863045 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.7835. Min Act: -0.1700

Data Index: 204972 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8147. Min Act: -0.1700

Data Index: 705914 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.7835. Min Act: -0.1700

Data Index: 682456 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8460. Min Act: -0.1700

Data Index: 631884 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8460. Min Act: -0.1700

Data Index: 613633 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 4.0649. Min Range: -4.0649

Max Act: 3.8460. Min Act: -0.1700

Data Index: 451696 (C4 (Web Text))

Max Activating Token Index: 464