Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.4097. Min Act: -0.1700

Data Index: 1451000 (Python Code)

Max Activating Token Index: 837

Text #1

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.4722. Min Act: -0.1700

Data Index: 1565091 (Python Code)

Max Activating Token Index: 275

Text #2

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.4097. Min Act: -0.1700

Data Index: 1533866 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2847. Min Act: -0.1700

Data Index: 1445965 (Python Code)

Max Activating Token Index: 981

Text #4

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.3004. Min Act: -0.1700

Data Index: 1650767 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.3629. Min Act: -0.1700

Data Index: 1471248 (Python Code)

Max Activating Token Index: 308

Text #6

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.1285. Min Act: -0.1700

Data Index: 1557929 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.3629. Min Act: -0.1700

Data Index: 1421540 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2691. Min Act: -0.1700

Data Index: 1612600 (Python Code)

Max Activating Token Index: 799

Text #9

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2066. Min Act: -0.1700

Data Index: 1527402 (Python Code)

Max Activating Token Index: 858

Text #10

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2691. Min Act: -0.1700

Data Index: 1531965 (Python Code)

Max Activating Token Index: 233

Text #11

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2066. Min Act: -0.1700

Data Index: 1538191 (Python Code)

Max Activating Token Index: 1020

Text #12

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2379. Min Act: -0.1700

Data Index: 1390029 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.3785. Min Act: -0.1700

Data Index: 1619737 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.1754. Min Act: -0.1700

Data Index: 1436416 (Python Code)

Max Activating Token Index: 140

Text #15

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.1754. Min Act: -0.1700

Data Index: 1361599 (Python Code)

Max Activating Token Index: 232

Text #16

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2847. Min Act: -0.1700

Data Index: 1400880 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2691. Min Act: -0.1700

Data Index: 1599018 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.1597. Min Act: -0.1700

Data Index: 1428897 (Python Code)

Max Activating Token Index: 717

Text #19

Max Range: 5.4722. Min Range: -5.4722

Max Act: 5.2066. Min Act: -0.1700

Data Index: 1624764 (Python Code)

Max Activating Token Index: 451