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

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

Neuron 451 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: 3.4302. Min Range: -3.4302

Max Act: 3.4302. Min Act: -0.1700

Data Index: 1629180 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.4097. Min Act: -0.1700

Data Index: 1374175 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.3089. Min Act: -0.1699

Data Index: 348506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.3307. Min Act: -0.1700

Data Index: 1455387 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2369. Min Act: -0.1699

Data Index: 1074315 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2370. Min Act: -0.1700

Data Index: 1521706 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2692. Min Act: -0.1695

Data Index: 1566750 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2348. Min Act: -0.1696

Data Index: 1628869 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2440. Min Act: -0.1699

Data Index: 1605362 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2258. Min Act: -0.1699

Data Index: 1648854 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.1732. Min Act: -0.1700

Data Index: 889975 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2011. Min Act: -0.1694

Data Index: 369245 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2227. Min Act: -0.1700

Data Index: 1019199 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.1709. Min Act: -0.1700

Data Index: 1597295 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2122. Min Act: -0.1698

Data Index: 1406738 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.2040. Min Act: -0.1698

Data Index: 1555495 (Python Code)

Max Activating Token Index: 418

Text #16

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.1692. Min Act: -0.1700

Data Index: 1530152 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.1718. Min Act: -0.1700

Data Index: 1426153 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.1832. Min Act: -0.1697

Data Index: 1634825 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.4302. Min Range: -3.4302

Max Act: 3.1867. Min Act: -0.1700

Data Index: 1507234 (Python Code)

Max Activating Token Index: 1023