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

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

Neuron 1594 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: 7.1713. Min Range: -7.1713

Max Act: 7.1713. Min Act: -0.1700

Data Index: 998953 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 7.1713. Min Range: -7.1713

Max Act: 7.0775. Min Act: -0.1700

Data Index: 891229 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 7.1713. Min Range: -7.1713

Max Act: 7.0463. Min Act: -0.1700

Data Index: 670253 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 7.1713. Min Range: -7.1713

Max Act: 7.0463. Min Act: -0.1700

Data Index: 1389189 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9213. Min Act: -0.1700

Data Index: 1207238 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9213. Min Act: -0.1700

Data Index: 741868 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9525. Min Act: -0.1700

Data Index: 1255838 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.8900. Min Act: -0.1700

Data Index: 767884 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 7.1713. Min Range: -7.1713

Max Act: 7.0463. Min Act: -0.1700

Data Index: 1232382 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9838. Min Act: -0.1700

Data Index: 1124127 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 7.1713. Min Range: -7.1713

Max Act: 7.0150. Min Act: -0.1700

Data Index: 1597865 (Python Code)

Max Activating Token Index: 152

Text #11

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9525. Min Act: -0.1700

Data Index: 1487364 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 7.1713. Min Range: -7.1713

Max Act: 7.0463. Min Act: -0.1700

Data Index: 1398796 (Python Code)

Max Activating Token Index: 437

Text #13

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9525. Min Act: -0.1700

Data Index: 1033791 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9213. Min Act: -0.1700

Data Index: 1070882 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9525. Min Act: -0.1700

Data Index: 750388 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 7.1713. Min Range: -7.1713

Max Act: 7.0775. Min Act: -0.1700

Data Index: 301496 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9525. Min Act: -0.1700

Data Index: 729772 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.9213. Min Act: -0.1700

Data Index: 443151 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 7.1713. Min Range: -7.1713

Max Act: 6.7963. Min Act: -0.1700

Data Index: 1032608 (C4 (Web Text))

Max Activating Token Index: 778