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

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

Neuron 1677 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: 5.8859. Min Range: -5.8859

Max Act: 5.8547. Min Act: -0.1699

Data Index: 1007587 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.8547. Min Act: -0.1699

Data Index: 79493 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.8078. Min Act: -0.1699

Data Index: 901579 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.7453. Min Act: -0.1699

Data Index: 795099 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.8859. Min Act: -0.1699

Data Index: 875450 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6515. Min Act: -0.1699

Data Index: 741239 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6984. Min Act: -0.1699

Data Index: 595698 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.7453. Min Act: -0.1699

Data Index: 591938 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.7140. Min Act: -0.1699

Data Index: 688882 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6828. Min Act: -0.1699

Data Index: 580181 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6515. Min Act: -0.1699

Data Index: 983459 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6984. Min Act: -0.1699

Data Index: 600659 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6828. Min Act: -0.1699

Data Index: 744263 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6047. Min Act: -0.1699

Data Index: 32195 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6203. Min Act: -0.1699

Data Index: 1027591 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6828. Min Act: -0.1699

Data Index: 1225017 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6047. Min Act: -0.1699

Data Index: 1077805 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6047. Min Act: -0.1699

Data Index: 999516 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.6047. Min Act: -0.1699

Data Index: 1071838 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 5.8859. Min Range: -5.8859

Max Act: 5.5734. Min Act: -0.1699

Data Index: 453616 (C4 (Web Text))

Max Activating Token Index: 119