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

Dataset: Open Web Text

Neuron 1434 in Layer 4

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: 4.8232. Min Range: -4.8232

Max Act: 4.8232. Min Act: -0.1700

Data Index: 4973917 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.3333. Min Act: -0.1700

Data Index: 801541 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.2242. Min Act: -0.1700

Data Index: 3829180 (Open Web Text)

Max Activating Token Index: 697

Text #3

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.2101. Min Act: -0.1700

Data Index: 5200685 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.1245. Min Act: -0.1700

Data Index: 187275 (Open Web Text)

Max Activating Token Index: 451

Text #5

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.1048. Min Act: -0.1700

Data Index: 2086437 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0738. Min Act: -0.1700

Data Index: 6875987 (Open Web Text)

Max Activating Token Index: 552

Text #7

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.1272. Min Act: -0.1700

Data Index: 1195794 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.1064. Min Act: -0.1700

Data Index: 5668484 (Open Web Text)

Max Activating Token Index: 889

Text #9

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0576. Min Act: -0.1700

Data Index: 6743097 (Open Web Text)

Max Activating Token Index: 220

Text #10

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.1082. Min Act: -0.1700

Data Index: 3621640 (Open Web Text)

Max Activating Token Index: 642

Text #11

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0712. Min Act: -0.1700

Data Index: 1851186 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0616. Min Act: -0.1700

Data Index: 6708698 (Open Web Text)

Max Activating Token Index: 933

Text #13

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0350. Min Act: -0.1700

Data Index: 1909070 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0950. Min Act: -0.1700

Data Index: 7078600 (Open Web Text)

Max Activating Token Index: 572

Text #15

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0616. Min Act: -0.1700

Data Index: 7877202 (Open Web Text)

Max Activating Token Index: 686

Text #16

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0404. Min Act: -0.1700

Data Index: 423207 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0449. Min Act: -0.1700

Data Index: 1200662 (Open Web Text)

Max Activating Token Index: 943

Text #18

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0607. Min Act: -0.1700

Data Index: 2491312 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 4.8232. Min Range: -4.8232

Max Act: 4.0359. Min Act: -0.1700

Data Index: 5143982 (Open Web Text)

Max Activating Token Index: 853