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

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

Neuron 504 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: 4.2799. Min Range: -4.2799

Max Act: 4.2799. Min Act: -0.1700

Data Index: 92587 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 4.2799. Min Range: -4.2799

Max Act: 4.1430. Min Act: -0.1700

Data Index: 617920 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 4.2799. Min Range: -4.2799

Max Act: 4.0675. Min Act: -0.1700

Data Index: 666448 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 4.2799. Min Range: -4.2799

Max Act: 4.0633. Min Act: -0.1700

Data Index: 1048059 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 4.2799. Min Range: -4.2799

Max Act: 4.0517. Min Act: -0.1700

Data Index: 69506 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 4.2799. Min Range: -4.2799

Max Act: 4.0378. Min Act: -0.1700

Data Index: 430312 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 4.2799. Min Range: -4.2799

Max Act: 4.0340. Min Act: -0.1700

Data Index: 800840 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 4.2799. Min Range: -4.2799

Max Act: 4.0153. Min Act: -0.1700

Data Index: 88690 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 4.2799. Min Range: -4.2799

Max Act: 4.0066. Min Act: -0.1700

Data Index: 186942 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.9727. Min Act: -0.1700

Data Index: 904268 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.8886. Min Act: -0.1700

Data Index: 913516 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.8629. Min Act: -0.1700

Data Index: 1398516 (Python Code)

Max Activating Token Index: 713

Text #12

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.8140. Min Act: -0.1700

Data Index: 126911 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.7827. Min Act: -0.1700

Data Index: 1598517 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.7398. Min Act: -0.1700

Data Index: 1566707 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.7222. Min Act: -0.1700

Data Index: 708924 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.7137. Min Act: -0.1700

Data Index: 558416 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.6817. Min Act: -0.1700

Data Index: 1513867 (Python Code)

Max Activating Token Index: 713

Text #18

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.6791. Min Act: -0.1700

Data Index: 1628456 (Python Code)

Max Activating Token Index: 85

Text #19

Max Range: 4.2799. Min Range: -4.2799

Max Act: 3.6682. Min Act: -0.1700

Data Index: 1513718 (Python Code)

Max Activating Token Index: 609