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

Dataset: Open Web Text

Neuron 2314 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: 3.8736. Min Range: -3.8736

Max Act: 3.8736. Min Act: -0.1700

Data Index: 4560266 (Open Web Text)

Max Activating Token Index: 833

Text #1

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7680. Min Act: -0.1700

Data Index: 2392120 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7406. Min Act: -0.1700

Data Index: 4447024 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.6319. Min Act: -0.1700

Data Index: 3281605 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.6163. Min Act: -0.1700

Data Index: 8418900 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.6016. Min Act: -0.1700

Data Index: 5667015 (Open Web Text)

Max Activating Token Index: 618

Text #6

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1626943 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.5344. Min Act: -0.1700

Data Index: 2358328 (Open Web Text)

Max Activating Token Index: 917

Text #8

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.5193. Min Act: -0.1700

Data Index: 3276700 (Open Web Text)

Max Activating Token Index: 797

Text #9

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.5316. Min Act: -0.1700

Data Index: 5253747 (Open Web Text)

Max Activating Token Index: 983

Text #10

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.5122. Min Act: -0.1700

Data Index: 6527733 (Open Web Text)

Max Activating Token Index: 704

Text #11

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.5118. Min Act: -0.1700

Data Index: 4538371 (Open Web Text)

Max Activating Token Index: 842

Text #12

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.5264. Min Act: -0.1700

Data Index: 6812083 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.5004. Min Act: -0.1700

Data Index: 2032905 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.4769. Min Act: -0.1700

Data Index: 5880307 (Open Web Text)

Max Activating Token Index: 885

Text #15

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.4781. Min Act: -0.1700

Data Index: 884610 (Open Web Text)

Max Activating Token Index: 908

Text #16

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.4592. Min Act: -0.1700

Data Index: 3264262 (Open Web Text)

Max Activating Token Index: 326

Text #17

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.4726. Min Act: -0.1700

Data Index: 1567285 (Open Web Text)

Max Activating Token Index: 975

Text #18

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.4707. Min Act: -0.1700

Data Index: 5614267 (Open Web Text)

Max Activating Token Index: 485

Text #19

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.4346. Min Act: -0.1700

Data Index: 8759917 (Open Web Text)

Max Activating Token Index: 1004