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

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

Neuron 148 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: 3.8247. Min Range: -3.8247

Max Act: 3.8247. Min Act: -0.1700

Data Index: 1648829 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7935. Min Act: -0.1700

Data Index: 924082 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7622. Min Act: -0.1700

Data Index: 1611942 (Python Code)

Max Activating Token Index: 527

Text #3

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7935. Min Act: -0.1700

Data Index: 1462817 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7309. Min Act: -0.1700

Data Index: 1249789 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7309. Min Act: -0.1700

Data Index: 1571805 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7309. Min Act: -0.1700

Data Index: 1444757 (Python Code)

Max Activating Token Index: 386

Text #7

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7152. Min Act: -0.1700

Data Index: 1373917 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7152. Min Act: -0.1700

Data Index: 1414704 (Python Code)

Max Activating Token Index: 771

Text #9

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6839. Min Act: -0.1700

Data Index: 1452852 (Python Code)

Max Activating Token Index: 954

Text #10

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6996. Min Act: -0.1700

Data Index: 1582809 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6839. Min Act: -0.1700

Data Index: 1180646 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6839. Min Act: -0.1700

Data Index: 1627626 (Python Code)

Max Activating Token Index: 755

Text #13

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1374110 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6370. Min Act: -0.1700

Data Index: 1367362 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6057. Min Act: -0.1700

Data Index: 1560030 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6213. Min Act: -0.1700

Data Index: 1549748 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.5744. Min Act: -0.1700

Data Index: 1490377 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6057. Min Act: -0.1700

Data Index: 1483794 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6213. Min Act: -0.1700

Data Index: 993848 (C4 (Web Text))

Max Activating Token Index: 687