Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 901 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.7165. Min Act: -0.1700

Data Index: 1244134 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.3727. Min Act: -0.1700

Data Index: 1309978 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.3415. Min Act: -0.1700

Data Index: 269458 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.3415. Min Act: -0.1700

Data Index: 1346755 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.3102. Min Act: -0.1700

Data Index: 699444 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.3102. Min Act: -0.1700

Data Index: 830703 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.2790. Min Act: -0.1700

Data Index: 319052 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.3102. Min Act: -0.1700

Data Index: 1023420 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.2477. Min Act: -0.1700

Data Index: 1076735 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.2477. Min Act: -0.1700

Data Index: 1286371 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.2477. Min Act: -0.1700

Data Index: 891082 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.2165. Min Act: -0.1700

Data Index: 571695 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.1852. Min Act: -0.1700

Data Index: 225762 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.2165. Min Act: -0.1700

Data Index: 1210404 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.1540. Min Act: -0.1700

Data Index: 420547 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.1852. Min Act: -0.1700

Data Index: 1264745 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.1540. Min Act: -0.1700

Data Index: 1337516 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.1540. Min Act: -0.1700

Data Index: 570104 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.1540. Min Act: -0.1700

Data Index: 1245454 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 5.7165. Min Range: -5.7165

Max Act: 5.1852. Min Act: -0.1700

Data Index: 60226 (C4 (Web Text))

Max Activating Token Index: 788