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

Dataset: Open Web Text

Neuron 1682 in Layer 2

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: 3.8828. Min Range: -3.8828

Max Act: 3.8828. Min Act: -0.1700

Data Index: 2767747 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.8380. Min Act: -0.1700

Data Index: 5421975 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7267. Min Act: -0.1700

Data Index: 5370915 (Open Web Text)

Max Activating Token Index: 728

Text #3

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7273. Min Act: -0.1700

Data Index: 3143511 (Open Web Text)

Max Activating Token Index: 764

Text #4

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7433. Min Act: -0.1700

Data Index: 6066715 (Open Web Text)

Max Activating Token Index: 310

Text #5

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6847. Min Act: -0.1700

Data Index: 501940 (Open Web Text)

Max Activating Token Index: 202

Text #6

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7025. Min Act: -0.1700

Data Index: 6972009 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6753. Min Act: -0.1700

Data Index: 3270084 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6658. Min Act: -0.1700

Data Index: 5829785 (Open Web Text)

Max Activating Token Index: 357

Text #9

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6689. Min Act: -0.1700

Data Index: 932978 (Open Web Text)

Max Activating Token Index: 473

Text #10

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6608. Min Act: -0.1700

Data Index: 916113 (Open Web Text)

Max Activating Token Index: 908

Text #11

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6601. Min Act: -0.1700

Data Index: 5354176 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6325. Min Act: -0.1700

Data Index: 6476708 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6382. Min Act: -0.1700

Data Index: 8800771 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6410. Min Act: -0.1700

Data Index: 1328017 (Open Web Text)

Max Activating Token Index: 875

Text #15

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6582. Min Act: -0.1700

Data Index: 244823 (Open Web Text)

Max Activating Token Index: 222

Text #16

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.5918. Min Act: -0.1700

Data Index: 3063815 (Open Web Text)

Max Activating Token Index: 340

Text #17

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.5956. Min Act: -0.1700

Data Index: 4425032 (Open Web Text)

Max Activating Token Index: 820

Text #18

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6056. Min Act: -0.1700

Data Index: 6644335 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6111. Min Act: -0.1700

Data Index: 4678228 (Open Web Text)

Max Activating Token Index: 523