Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1801 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1515. Min Act: -0.1673

Data Index: 4652286 (Open Web Text)

Max Activating Token Index: 474

Text #1

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1345. Min Act: -0.1516

Data Index: 963642 (Open Web Text)

Max Activating Token Index: 218

Text #2

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1210. Min Act: -0.1558

Data Index: 7960208 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1202. Min Act: -0.1700

Data Index: 2870890 (Open Web Text)

Max Activating Token Index: 46

Text #4

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1201. Min Act: -0.1617

Data Index: 3647827 (Open Web Text)

Max Activating Token Index: 53

Text #5

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1123. Min Act: -0.1700

Data Index: 6438575 (Open Web Text)

Max Activating Token Index: 59

Text #6

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1060. Min Act: -0.1583

Data Index: 6176662 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0904. Min Act: -0.1550

Data Index: 719181 (Open Web Text)

Max Activating Token Index: 34

Text #8

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0936. Min Act: -0.1621

Data Index: 2511283 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0825. Min Act: -0.1627

Data Index: 2612432 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0964. Min Act: -0.1612

Data Index: 8518541 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0835. Min Act: -0.1547

Data Index: 516857 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0857. Min Act: -0.1577

Data Index: 1367104 (Open Web Text)

Max Activating Token Index: 37

Text #13

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0889. Min Act: -0.1607

Data Index: 7038482 (Open Web Text)

Max Activating Token Index: 80

Text #14

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0776. Min Act: -0.1606

Data Index: 2853657 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0827. Min Act: -0.1533

Data Index: 2622395 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0796. Min Act: -0.1516

Data Index: 2004703 (Open Web Text)

Max Activating Token Index: 597

Text #17

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0781. Min Act: -0.1659

Data Index: 5477188 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0736. Min Act: -0.1606

Data Index: 5188338 (Open Web Text)

Max Activating Token Index: 74

Text #19

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0767. Min Act: -0.1697

Data Index: 901434 (Open Web Text)

Max Activating Token Index: 51