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

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

Neuron 1937 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: 3.0688. Min Range: -3.0688

Max Act: 3.0688. Min Act: -0.1700

Data Index: 648874 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0530. Min Act: -0.1700

Data Index: 1317250 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0530. Min Act: -0.1700

Data Index: 223286 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0372. Min Act: -0.1700

Data Index: 1263896 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0214. Min Act: -0.1700

Data Index: 1344663 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0056. Min Act: -0.1700

Data Index: 400161 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0214. Min Act: -0.1700

Data Index: 826533 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0214. Min Act: -0.1700

Data Index: 520313 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0214. Min Act: -0.1700

Data Index: 351875 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0056. Min Act: -0.1700

Data Index: 714357 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0056. Min Act: -0.1700

Data Index: 31002 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 3.0688. Min Range: -3.0688

Max Act: 2.9740. Min Act: -0.1700

Data Index: 533552 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 3.0688. Min Range: -3.0688

Max Act: 2.9898. Min Act: -0.1700

Data Index: 397827 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 3.0688. Min Range: -3.0688

Max Act: 2.9898. Min Act: -0.1700

Data Index: 39815 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 3.0688. Min Range: -3.0688

Max Act: 2.9898. Min Act: -0.1700

Data Index: 67445 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 3.0688. Min Range: -3.0688

Max Act: 2.9898. Min Act: -0.1700

Data Index: 1100556 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 3.0688. Min Range: -3.0688

Max Act: 2.9740. Min Act: -0.1700

Data Index: 489868 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0056. Min Act: -0.1700

Data Index: 181217 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0056. Min Act: -0.1700

Data Index: 458988 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 3.0688. Min Range: -3.0688

Max Act: 3.0056. Min Act: -0.1700

Data Index: 988109 (C4 (Web Text))

Max Activating Token Index: 171