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

Dataset: Open Web Text

Neuron 1858 in Layer 1

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: 4.8297. Min Range: -4.8297

Max Act: 4.8297. Min Act: -0.1700

Data Index: 3608304 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.7096. Min Act: -0.1700

Data Index: 3694347 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.6649. Min Act: -0.1691

Data Index: 3310879 (Open Web Text)

Max Activating Token Index: 767

Text #3

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.6388. Min Act: -0.1700

Data Index: 1810062 (Open Web Text)

Max Activating Token Index: 916

Text #4

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.6564. Min Act: -0.1700

Data Index: 7241437 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.5715. Min Act: -0.1700

Data Index: 1990476 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.5886. Min Act: -0.1700

Data Index: 4335435 (Open Web Text)

Max Activating Token Index: 604

Text #7

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.6036. Min Act: -0.1700

Data Index: 8784026 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.5210. Min Act: -0.1700

Data Index: 5797454 (Open Web Text)

Max Activating Token Index: 639

Text #9

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.5629. Min Act: -0.1700

Data Index: 8352793 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.5158. Min Act: -0.1700

Data Index: 2112176 (Open Web Text)

Max Activating Token Index: 835

Text #11

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.4910. Min Act: -0.1700

Data Index: 1470683 (Open Web Text)

Max Activating Token Index: 504

Text #12

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.4792. Min Act: -0.1700

Data Index: 213428 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.4764. Min Act: -0.1700

Data Index: 5726150 (Open Web Text)

Max Activating Token Index: 610

Text #14

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.4812. Min Act: -0.1700

Data Index: 3357328 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.5019. Min Act: -0.1700

Data Index: 3365972 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.4408. Min Act: -0.1559

Data Index: 8249997 (Open Web Text)

Max Activating Token Index: 625

Text #17

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.4657. Min Act: -0.1700

Data Index: 755779 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.4262. Min Act: -0.1700

Data Index: 4480179 (Open Web Text)

Max Activating Token Index: 839

Text #19

Max Range: 4.8297. Min Range: -4.8297

Max Act: 4.4053. Min Act: -0.1700

Data Index: 622104 (Open Web Text)

Max Activating Token Index: 442