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

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

Neuron 1730 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: 6.3013. Min Range: -6.3013

Max Act: 6.2585. Min Act: -0.1699

Data Index: 1483566 (Python Code)

Max Activating Token Index: 254

Text #1

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.2841. Min Act: -0.1695

Data Index: 1374996 (Python Code)

Max Activating Token Index: 409

Text #2

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.3013. Min Act: -0.1700

Data Index: 1566392 (Python Code)

Max Activating Token Index: 901

Text #3

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.1988. Min Act: -0.1700

Data Index: 151547 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.1996. Min Act: -0.1695

Data Index: 1598296 (Python Code)

Max Activating Token Index: 572

Text #5

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.2524. Min Act: -0.1680

Data Index: 1595540 (Python Code)

Max Activating Token Index: 292

Text #6

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.2471. Min Act: -0.1669

Data Index: 1419390 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.2024. Min Act: -0.1700

Data Index: 1562381 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.1713. Min Act: -0.1700

Data Index: 1135457 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.1736. Min Act: -0.1700

Data Index: 1582298 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.1504. Min Act: -0.1700

Data Index: 1609115 (Python Code)

Max Activating Token Index: 619

Text #11

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.1275. Min Act: -0.1685

Data Index: 1645235 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.0891. Min Act: -0.1695

Data Index: 1458728 (Python Code)

Max Activating Token Index: 242

Text #13

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.1115. Min Act: -0.1700

Data Index: 1436817 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.0841. Min Act: -0.1691

Data Index: 1368719 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 6.3013. Min Range: -6.3013

Max Act: 6.0631. Min Act: -0.1700

Data Index: 1194538 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 6.3013. Min Range: -6.3013

Max Act: 5.9909. Min Act: -0.1700

Data Index: 579188 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 6.3013. Min Range: -6.3013

Max Act: 5.9648. Min Act: -0.1700

Data Index: 548437 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 6.3013. Min Range: -6.3013

Max Act: 5.9710. Min Act: -0.1700

Data Index: 371758 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 6.3013. Min Range: -6.3013

Max Act: 5.9606. Min Act: -0.1700

Data Index: 14649 (C4 (Web Text))

Max Activating Token Index: 289