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

Dataset: Open Web Text

Neuron 395 in Layer 6

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: 6.0985. Min Range: -6.0985

Max Act: 6.0985. Min Act: -0.1700

Data Index: 5554046 (Open Web Text)

Max Activating Token Index: 976

Text #1

Max Range: 6.0985. Min Range: -6.0985

Max Act: 6.0651. Min Act: -0.1700

Data Index: 739313 (Open Web Text)

Max Activating Token Index: 264

Text #2

Max Range: 6.0985. Min Range: -6.0985

Max Act: 6.0313. Min Act: -0.1700

Data Index: 6859983 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 6.0985. Min Range: -6.0985

Max Act: 6.0260. Min Act: -0.1700

Data Index: 2631763 (Open Web Text)

Max Activating Token Index: 470

Text #4

Max Range: 6.0985. Min Range: -6.0985

Max Act: 6.0064. Min Act: -0.1700

Data Index: 3700231 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 6.0985. Min Range: -6.0985

Max Act: 6.0038. Min Act: -0.1700

Data Index: 1375899 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 6.0985. Min Range: -6.0985

Max Act: 6.0163. Min Act: -0.1700

Data Index: 1179072 (Open Web Text)

Max Activating Token Index: 499

Text #7

Max Range: 6.0985. Min Range: -6.0985

Max Act: 6.0023. Min Act: -0.1700

Data Index: 4888709 (Open Web Text)

Max Activating Token Index: 735

Text #8

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9768. Min Act: -0.1700

Data Index: 1861324 (Open Web Text)

Max Activating Token Index: 413

Text #9

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9822. Min Act: -0.1700

Data Index: 6848978 (Open Web Text)

Max Activating Token Index: 544

Text #10

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9791. Min Act: -0.1700

Data Index: 8525854 (Open Web Text)

Max Activating Token Index: 365

Text #11

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9816. Min Act: -0.1700

Data Index: 3483707 (Open Web Text)

Max Activating Token Index: 651

Text #12

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9403. Min Act: -0.1700

Data Index: 3082961 (Open Web Text)

Max Activating Token Index: 748

Text #13

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9489. Min Act: -0.1700

Data Index: 411734 (Open Web Text)

Max Activating Token Index: 537

Text #14

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9390. Min Act: -0.1700

Data Index: 8638546 (Open Web Text)

Max Activating Token Index: 337

Text #15

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9134. Min Act: -0.1700

Data Index: 1895704 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9410. Min Act: -0.1700

Data Index: 473702 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9544. Min Act: -0.1700

Data Index: 6499494 (Open Web Text)

Max Activating Token Index: 372

Text #18

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9072. Min Act: -0.1700

Data Index: 5593409 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 6.0985. Min Range: -6.0985

Max Act: 5.9004. Min Act: -0.1700

Data Index: 5664711 (Open Web Text)

Max Activating Token Index: 470