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

Dataset: Open Web Text

Neuron 2706 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: 3.1076. Min Range: -3.1076

Max Act: 3.1076. Min Act: -0.1700

Data Index: 2542957 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 3.1076. Min Range: -3.1076

Max Act: 3.0530. Min Act: -0.1700

Data Index: 2568094 (Open Web Text)

Max Activating Token Index: 140

Text #2

Max Range: 3.1076. Min Range: -3.1076

Max Act: 3.0406. Min Act: -0.1700

Data Index: 6206606 (Open Web Text)

Max Activating Token Index: 178

Text #3

Max Range: 3.1076. Min Range: -3.1076

Max Act: 3.0250. Min Act: -0.1700

Data Index: 2330741 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1310779 (Open Web Text)

Max Activating Token Index: 568

Text #5

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9892. Min Act: -0.1700

Data Index: 3363964 (Open Web Text)

Max Activating Token Index: 821

Text #6

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9839. Min Act: -0.1700

Data Index: 2190745 (Open Web Text)

Max Activating Token Index: 712

Text #7

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9996. Min Act: -0.1700

Data Index: 6244414 (Open Web Text)

Max Activating Token Index: 631

Text #8

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9875. Min Act: -0.1700

Data Index: 2238487 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9518. Min Act: -0.1700

Data Index: 3258840 (Open Web Text)

Max Activating Token Index: 474

Text #10

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9724. Min Act: -0.1700

Data Index: 6362003 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9475. Min Act: -0.1700

Data Index: 6728450 (Open Web Text)

Max Activating Token Index: 298

Text #12

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9390. Min Act: -0.1700

Data Index: 3647480 (Open Web Text)

Max Activating Token Index: 697

Text #13

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9446. Min Act: -0.1700

Data Index: 3891003 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9301. Min Act: -0.1700

Data Index: 5316661 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9197. Min Act: -0.1700

Data Index: 7246037 (Open Web Text)

Max Activating Token Index: 516

Text #16

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9234. Min Act: -0.1700

Data Index: 1248986 (Open Web Text)

Max Activating Token Index: 706

Text #17

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.8964. Min Act: -0.1700

Data Index: 853195 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9364. Min Act: -0.1700

Data Index: 682935 (Open Web Text)

Max Activating Token Index: 678

Text #19

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9270. Min Act: -0.1700

Data Index: 2904334 (Open Web Text)

Max Activating Token Index: 557