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

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

Neuron 512 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: 3.4866. Min Range: -3.4866

Max Act: 3.4866. Min Act: -0.1699

Data Index: 1385622 (Python Code)

Max Activating Token Index: 720

Text #1

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1408121 (Python Code)

Max Activating Token Index: 432

Text #2

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.2996. Min Act: -0.1699

Data Index: 1476324 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.2270. Min Act: -0.1700

Data Index: 1640434 (Python Code)

Max Activating Token Index: 143

Text #4

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.2207. Min Act: -0.1698

Data Index: 1457696 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1854. Min Act: -0.1700

Data Index: 1620081 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1667. Min Act: -0.1699

Data Index: 1583221 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1651. Min Act: -0.1700

Data Index: 1630096 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1747. Min Act: -0.1700

Data Index: 1423929 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1808. Min Act: -0.1700

Data Index: 1550108 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1798. Min Act: -0.1700

Data Index: 1462220 (Python Code)

Max Activating Token Index: 594

Text #11

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1613. Min Act: -0.1696

Data Index: 1373175 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1500. Min Act: -0.1700

Data Index: 1530401 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1512. Min Act: -0.1693

Data Index: 1512973 (Python Code)

Max Activating Token Index: 267

Text #14

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1708. Min Act: -0.1700

Data Index: 1479136 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1656. Min Act: -0.1697

Data Index: 1624523 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1428. Min Act: -0.1699

Data Index: 315028 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1320. Min Act: -0.1700

Data Index: 1629479 (Python Code)

Max Activating Token Index: 952

Text #18

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1439. Min Act: -0.1700

Data Index: 1394700 (Python Code)

Max Activating Token Index: 305

Text #19

Max Range: 3.4866. Min Range: -3.4866

Max Act: 3.1405. Min Act: -0.1700

Data Index: 1369774 (Python Code)

Max Activating Token Index: 891