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

Dataset: Open Web Text

Neuron 2713 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: 3.9056. Min Range: -3.9056

Max Act: 3.9056. Min Act: -0.1700

Data Index: 5250743 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8284. Min Act: -0.1700

Data Index: 7713485 (Open Web Text)

Max Activating Token Index: 415

Text #2

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8482. Min Act: -0.1700

Data Index: 716069 (Open Web Text)

Max Activating Token Index: 566

Text #3

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8252. Min Act: -0.1700

Data Index: 4682386 (Open Web Text)

Max Activating Token Index: 607

Text #4

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.8153. Min Act: -0.1700

Data Index: 8280983 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7866. Min Act: -0.1700

Data Index: 619115 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7990. Min Act: -0.1700

Data Index: 5558175 (Open Web Text)

Max Activating Token Index: 390

Text #7

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7649. Min Act: -0.1700

Data Index: 2429300 (Open Web Text)

Max Activating Token Index: 609

Text #8

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7690. Min Act: -0.1700

Data Index: 3682919 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7612. Min Act: -0.1700

Data Index: 4094359 (Open Web Text)

Max Activating Token Index: 169

Text #10

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7742. Min Act: -0.1700

Data Index: 6625019 (Open Web Text)

Max Activating Token Index: 750

Text #11

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7806. Min Act: -0.1700

Data Index: 2989817 (Open Web Text)

Max Activating Token Index: 778

Text #12

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7734. Min Act: -0.1700

Data Index: 1570040 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7480. Min Act: -0.1700

Data Index: 2054921 (Open Web Text)

Max Activating Token Index: 241

Text #14

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7328. Min Act: -0.1700

Data Index: 6721840 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7411. Min Act: -0.1700

Data Index: 3678948 (Open Web Text)

Max Activating Token Index: 816

Text #16

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7529. Min Act: -0.1700

Data Index: 912708 (Open Web Text)

Max Activating Token Index: 571

Text #17

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7486. Min Act: -0.1700

Data Index: 4447456 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7569. Min Act: -0.1700

Data Index: 2525675 (Open Web Text)

Max Activating Token Index: 584

Text #19

Max Range: 3.9056. Min Range: -3.9056

Max Act: 3.7581. Min Act: -0.1700

Data Index: 4481129 (Open Web Text)

Max Activating Token Index: 711