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

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

Neuron 725 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.3687. Min Act: -0.1700

Data Index: 278270 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2587. Min Act: -0.1700

Data Index: 424277 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2116. Min Act: -0.1700

Data Index: 11967 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.2116. Min Act: -0.1700

Data Index: 75482 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1958. Min Act: -0.1700

Data Index: 644423 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1801. Min Act: -0.1700

Data Index: 449152 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1958. Min Act: -0.1700

Data Index: 934101 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1644. Min Act: -0.1700

Data Index: 622779 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1329. Min Act: -0.1700

Data Index: 312354 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1171. Min Act: -0.1700

Data Index: 948787 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1171. Min Act: -0.1700

Data Index: 238280 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1329. Min Act: -0.1700

Data Index: 944718 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1171. Min Act: -0.1700

Data Index: 1321410 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1171. Min Act: -0.1700

Data Index: 11027 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1171. Min Act: -0.1700

Data Index: 848410 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1013. Min Act: -0.1700

Data Index: 972175 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1013. Min Act: -0.1700

Data Index: 639977 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1013. Min Act: -0.1700

Data Index: 1182574 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.0856. Min Act: -0.1700

Data Index: 1269696 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1013. Min Act: -0.1700

Data Index: 520505 (C4 (Web Text))

Max Activating Token Index: 845