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

Dataset: Open Web Text

Neuron 2170 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: 4.7258. Min Range: -4.7258

Max Act: 4.7142. Min Act: -0.1699

Data Index: 1494073 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.7253. Min Act: -0.1700

Data Index: 1601060 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.7258. Min Act: -0.1700

Data Index: 1308438 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6842. Min Act: -0.1700

Data Index: 5478442 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.7226. Min Act: -0.1700

Data Index: 6791761 (Open Web Text)

Max Activating Token Index: 996

Text #5

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6771. Min Act: -0.1700

Data Index: 2129516 (Open Web Text)

Max Activating Token Index: 645

Text #6

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6921. Min Act: -0.1700

Data Index: 4966091 (Open Web Text)

Max Activating Token Index: 324

Text #7

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6454. Min Act: -0.1700

Data Index: 3073507 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6607. Min Act: -0.1700

Data Index: 2055814 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6621. Min Act: -0.1700

Data Index: 6672894 (Open Web Text)

Max Activating Token Index: 512

Text #10

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6512. Min Act: -0.1700

Data Index: 7844186 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6783. Min Act: -0.1700

Data Index: 7668570 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6234. Min Act: -0.1700

Data Index: 5934475 (Open Web Text)

Max Activating Token Index: 437

Text #13

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6075. Min Act: -0.1700

Data Index: 1041443 (Open Web Text)

Max Activating Token Index: 126

Text #14

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6184. Min Act: -0.1700

Data Index: 2417624 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6253. Min Act: -0.1700

Data Index: 890869 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6426. Min Act: -0.1699

Data Index: 575122 (Open Web Text)

Max Activating Token Index: 483

Text #17

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6492. Min Act: -0.1700

Data Index: 4251744 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6228. Min Act: -0.1700

Data Index: 5814657 (Open Web Text)

Max Activating Token Index: 711

Text #19

Max Range: 4.7258. Min Range: -4.7258

Max Act: 4.6027. Min Act: -0.1700

Data Index: 6924347 (Open Web Text)

Max Activating Token Index: 823