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

Dataset: Open Web Text

Neuron 580 in Layer 6

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: 3.5695. Min Range: -3.5695

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1349080 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5249. Min Act: -0.1700

Data Index: 7196923 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5355. Min Act: -0.1700

Data Index: 4996301 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5113. Min Act: -0.1700

Data Index: 5692970 (Open Web Text)

Max Activating Token Index: 46

Text #4

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5258. Min Act: -0.1700

Data Index: 6039958 (Open Web Text)

Max Activating Token Index: 302

Text #5

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5096. Min Act: -0.1700

Data Index: 6403984 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5167. Min Act: -0.1700

Data Index: 7299316 (Open Web Text)

Max Activating Token Index: 293

Text #7

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5007. Min Act: -0.1700

Data Index: 2602347 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5090. Min Act: -0.1700

Data Index: 6540937 (Open Web Text)

Max Activating Token Index: 124

Text #9

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5027. Min Act: -0.1700

Data Index: 828279 (Open Web Text)

Max Activating Token Index: 552

Text #10

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4911. Min Act: -0.1700

Data Index: 6456211 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4889. Min Act: -0.1700

Data Index: 4875213 (Open Web Text)

Max Activating Token Index: 609

Text #12

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5112. Min Act: -0.1700

Data Index: 3942306 (Open Web Text)

Max Activating Token Index: 778

Text #13

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4989. Min Act: -0.1700

Data Index: 1051632 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4803. Min Act: -0.1700

Data Index: 4174755 (Open Web Text)

Max Activating Token Index: 348

Text #15

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4823. Min Act: -0.1700

Data Index: 544126 (Open Web Text)

Max Activating Token Index: 617

Text #16

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5060. Min Act: -0.1700

Data Index: 2539597 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5037. Min Act: -0.1700

Data Index: 5844260 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5036. Min Act: -0.1700

Data Index: 2689255 (Open Web Text)

Max Activating Token Index: 1007

Text #19

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4632. Min Act: -0.1700

Data Index: 7193201 (Open Web Text)

Max Activating Token Index: 59