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

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

Neuron 799 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: 2.7546. Min Range: -2.7546

Max Act: 2.7546. Min Act: -0.1700

Data Index: 1498445 (Python Code)

Max Activating Token Index: 243

Text #1

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.7351. Min Act: -0.1700

Data Index: 1370058 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.7286. Min Act: -0.1700

Data Index: 1564385 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.7057. Min Act: -0.1666

Data Index: 1323091 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6978. Min Act: -0.1365

Data Index: 587183 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6559. Min Act: -0.1700

Data Index: 1531337 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6590. Min Act: -0.1537

Data Index: 588558 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6532. Min Act: -0.1365

Data Index: 199019 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6458. Min Act: -0.1700

Data Index: 927787 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6413. Min Act: -0.1700

Data Index: 1546333 (Python Code)

Max Activating Token Index: 247

Text #10

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6420. Min Act: -0.1697

Data Index: 613002 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6456. Min Act: -0.1699

Data Index: 7770 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6374. Min Act: -0.1700

Data Index: 972812 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6384. Min Act: -0.1699

Data Index: 608922 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6284. Min Act: -0.1699

Data Index: 337241 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6194. Min Act: -0.1700

Data Index: 1518652 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6055. Min Act: -0.1699

Data Index: 1462424 (Python Code)

Max Activating Token Index: 873

Text #17

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.6028. Min Act: -0.1699

Data Index: 1652952 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.5777. Min Act: -0.1700

Data Index: 1400088 (Python Code)

Max Activating Token Index: 949

Text #19

Max Range: 2.7546. Min Range: -2.7546

Max Act: 2.5839. Min Act: -0.1697

Data Index: 1559421 (Python Code)

Max Activating Token Index: 728