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

Dataset: Open Web Text

Neuron 797 in Layer 3

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: 3.9668. Min Range: -3.9668

Max Act: 3.9668. Min Act: -0.1700

Data Index: 1225512 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.9274. Min Act: -0.1700

Data Index: 7311401 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.8264. Min Act: -0.1700

Data Index: 8596128 (Open Web Text)

Max Activating Token Index: 485

Text #3

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.8284. Min Act: -0.1700

Data Index: 8659065 (Open Web Text)

Max Activating Token Index: 280

Text #4

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.8304. Min Act: -0.1700

Data Index: 7920681 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.7669. Min Act: -0.1700

Data Index: 3745981 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.7938. Min Act: -0.1700

Data Index: 7568262 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.7778. Min Act: -0.1700

Data Index: 7171329 (Open Web Text)

Max Activating Token Index: 398

Text #8

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.7194. Min Act: -0.1700

Data Index: 3825100 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.7195. Min Act: -0.1700

Data Index: 8153416 (Open Web Text)

Max Activating Token Index: 597

Text #10

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.7499. Min Act: -0.1700

Data Index: 5149631 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.7362. Min Act: -0.1700

Data Index: 595959 (Open Web Text)

Max Activating Token Index: 200

Text #12

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.7318. Min Act: -0.1700

Data Index: 4065916 (Open Web Text)

Max Activating Token Index: 218

Text #13

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.6900. Min Act: -0.1700

Data Index: 6404787 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.6730. Min Act: -0.1700

Data Index: 2741799 (Open Web Text)

Max Activating Token Index: 228

Text #15

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.6548. Min Act: -0.1700

Data Index: 4161158 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.6860. Min Act: -0.1700

Data Index: 5867380 (Open Web Text)

Max Activating Token Index: 293

Text #17

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.6551. Min Act: -0.1700

Data Index: 3275630 (Open Web Text)

Max Activating Token Index: 812

Text #18

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.6821. Min Act: -0.1700

Data Index: 3384636 (Open Web Text)

Max Activating Token Index: 645

Text #19

Max Range: 3.9668. Min Range: -3.9668

Max Act: 3.6784. Min Act: -0.1700

Data Index: 1568549 (Open Web Text)

Max Activating Token Index: 925