Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1965 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.2015. Min Act: -0.1700

Data Index: 1496046 (Python Code)

Max Activating Token Index: 788

Text #1

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1683. Min Act: -0.1700

Data Index: 547695 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1687. Min Act: -0.1700

Data Index: 1447204 (Python Code)

Max Activating Token Index: 629

Text #3

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1540. Min Act: -0.1700

Data Index: 566267 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1389. Min Act: -0.1699

Data Index: 1569442 (Python Code)

Max Activating Token Index: 462

Text #5

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1397. Min Act: -0.1700

Data Index: 776881 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1346. Min Act: -0.1700

Data Index: 923477 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0899. Min Act: -0.1700

Data Index: 1576262 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0885. Min Act: -0.1700

Data Index: 1402556 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1055. Min Act: -0.1699

Data Index: 1539673 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0770. Min Act: -0.1700

Data Index: 1035700 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0871. Min Act: -0.1700

Data Index: 1486328 (Python Code)

Max Activating Token Index: 837

Text #12

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0801. Min Act: -0.1700

Data Index: 12380 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0686. Min Act: -0.1700

Data Index: 1655879 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0680. Min Act: -0.1700

Data Index: 1490804 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0571. Min Act: -0.1700

Data Index: 1501921 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0448. Min Act: -0.1699

Data Index: 470501 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0460. Min Act: -0.1700

Data Index: 1436897 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0480. Min Act: -0.1700

Data Index: 1369450 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0537. Min Act: -0.1700

Data Index: 1007543 (C4 (Web Text))

Max Activating Token Index: 816