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

Dataset: Open Web Text

Neuron 2066 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: 3.3126. Min Range: -3.3126

Max Act: 3.3126. Min Act: -0.1700

Data Index: 4287914 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.3072. Min Act: -0.1700

Data Index: 4384207 (Open Web Text)

Max Activating Token Index: 121

Text #2

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2718. Min Act: -0.1700

Data Index: 8199759 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2603. Min Act: -0.1700

Data Index: 7669770 (Open Web Text)

Max Activating Token Index: 824

Text #4

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2353. Min Act: -0.1700

Data Index: 5073580 (Open Web Text)

Max Activating Token Index: 53

Text #5

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2271. Min Act: -0.1700

Data Index: 5473802 (Open Web Text)

Max Activating Token Index: 681

Text #6

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2049. Min Act: -0.1700

Data Index: 6395910 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2072. Min Act: -0.1700

Data Index: 6472091 (Open Web Text)

Max Activating Token Index: 139

Text #8

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1843. Min Act: -0.1700

Data Index: 7880989 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1882. Min Act: -0.1700

Data Index: 5375185 (Open Web Text)

Max Activating Token Index: 213

Text #10

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1797. Min Act: -0.1700

Data Index: 6250663 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1797. Min Act: -0.1700

Data Index: 8027018 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1787. Min Act: -0.1700

Data Index: 6086768 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1684. Min Act: -0.1700

Data Index: 6302126 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1500. Min Act: -0.1700

Data Index: 7152516 (Open Web Text)

Max Activating Token Index: 266

Text #15

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1538. Min Act: -0.1700

Data Index: 8141529 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1654. Min Act: -0.1700

Data Index: 1520977 (Open Web Text)

Max Activating Token Index: 803

Text #17

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1385. Min Act: -0.1700

Data Index: 7680114 (Open Web Text)

Max Activating Token Index: 347

Text #18

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1636. Min Act: -0.1700

Data Index: 5314805 (Open Web Text)

Max Activating Token Index: 968

Text #19

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1355. Min Act: -0.1700

Data Index: 419625 (Open Web Text)

Max Activating Token Index: 369