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

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

Neuron 496 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: 3.2311. Min Range: -3.2311

Max Act: 3.2311. Min Act: -0.1700

Data Index: 1474258 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.1275. Min Act: -0.1699

Data Index: 1472064 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.1488. Min Act: -0.1700

Data Index: 1426161 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.1070. Min Act: -0.1696

Data Index: 1648196 (Python Code)

Max Activating Token Index: 362

Text #4

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0640. Min Act: -0.1700

Data Index: 1415231 (Python Code)

Max Activating Token Index: 544

Text #5

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0780. Min Act: -0.1699

Data Index: 1574781 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0632. Min Act: -0.1700

Data Index: 1490745 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0709. Min Act: -0.1700

Data Index: 1632882 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0324. Min Act: -0.1686

Data Index: 1528225 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0325. Min Act: -0.1687

Data Index: 1514318 (Python Code)

Max Activating Token Index: 497

Text #10

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0246. Min Act: -0.1651

Data Index: 1554675 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0166. Min Act: -0.1692

Data Index: 1567987 (Python Code)

Max Activating Token Index: 1020

Text #12

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0393. Min Act: -0.1700

Data Index: 1571318 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0590. Min Act: -0.1624

Data Index: 1394682 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0088. Min Act: -0.1699

Data Index: 1459539 (Python Code)

Max Activating Token Index: 774

Text #15

Max Range: 3.2311. Min Range: -3.2311

Max Act: 2.9885. Min Act: -0.1700

Data Index: 1594546 (Python Code)

Max Activating Token Index: 804

Text #16

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0148. Min Act: -0.1697

Data Index: 1499896 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0013. Min Act: -0.1700

Data Index: 1483019 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 3.2311. Min Range: -3.2311

Max Act: 3.0015. Min Act: -0.1700

Data Index: 1405559 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 3.2311. Min Range: -3.2311

Max Act: 2.9988. Min Act: -0.1697

Data Index: 1614554 (Python Code)

Max Activating Token Index: 495