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

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

Neuron 1732 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.8006. Min Act: -0.1700

Data Index: 1025329 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.7067. Min Act: -0.1700

Data Index: 613979 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.7067. Min Act: -0.1700

Data Index: 270903 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.7380. Min Act: -0.1700

Data Index: 9283 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.7380. Min Act: -0.1700

Data Index: 902135 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.7067. Min Act: -0.1700

Data Index: 187038 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6441. Min Act: -0.1700

Data Index: 91093 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6441. Min Act: -0.1700

Data Index: 224240 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6441. Min Act: -0.1700

Data Index: 34309 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6441. Min Act: -0.1700

Data Index: 404956 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6128. Min Act: -0.1700

Data Index: 625506 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6128. Min Act: -0.1700

Data Index: 1162103 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6441. Min Act: -0.1700

Data Index: 293571 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.5815. Min Act: -0.1700

Data Index: 1051668 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6128. Min Act: -0.1700

Data Index: 236859 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.6128. Min Act: -0.1700

Data Index: 98748 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.5815. Min Act: -0.1700

Data Index: 95328 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.5815. Min Act: -0.1700

Data Index: 545698 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.5815. Min Act: -0.1700

Data Index: 1143184 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 3.8006. Min Range: -3.8006

Max Act: 3.5815. Min Act: -0.1700

Data Index: 511652 (C4 (Web Text))

Max Activating Token Index: 228