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

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

Neuron 1821 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: 4.5012. Min Range: -4.5012

Max Act: 4.5012. Min Act: -0.1700

Data Index: 1529394 (Python Code)

Max Activating Token Index: 496

Text #1

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3989. Min Act: -0.1700

Data Index: 1429473 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.4153. Min Act: -0.1700

Data Index: 1642364 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.4255. Min Act: -0.1700

Data Index: 1525662 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.4029. Min Act: -0.1700

Data Index: 1363236 (Python Code)

Max Activating Token Index: 725

Text #5

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3962. Min Act: -0.1700

Data Index: 1474443 (Python Code)

Max Activating Token Index: 308

Text #6

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3781. Min Act: -0.1700

Data Index: 1592442 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3475. Min Act: -0.1700

Data Index: 1393738 (Python Code)

Max Activating Token Index: 475

Text #8

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3852. Min Act: -0.1700

Data Index: 1475436 (Python Code)

Max Activating Token Index: 205

Text #9

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3831. Min Act: -0.1700

Data Index: 1623603 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.4058. Min Act: -0.1700

Data Index: 1497310 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3430. Min Act: -0.1700

Data Index: 1368734 (Python Code)

Max Activating Token Index: 754

Text #12

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3476. Min Act: -0.1700

Data Index: 1626780 (Python Code)

Max Activating Token Index: 598

Text #13

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3545. Min Act: -0.1700

Data Index: 1575200 (Python Code)

Max Activating Token Index: 757

Text #14

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3349. Min Act: -0.1700

Data Index: 1500146 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3325. Min Act: -0.1700

Data Index: 1363595 (Python Code)

Max Activating Token Index: 495

Text #16

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3321. Min Act: -0.1700

Data Index: 1534209 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.3452. Min Act: -0.1700

Data Index: 1363896 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.2981. Min Act: -0.1700

Data Index: 1458631 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 4.5012. Min Range: -4.5012

Max Act: 4.2933. Min Act: -0.1700

Data Index: 1363151 (Python Code)

Max Activating Token Index: 231