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

Dataset: Open Web Text

Neuron 259 in Layer 4

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: 3.0456. Min Range: -3.0456

Max Act: 3.0310. Min Act: -0.1700

Data Index: 2764859 (Open Web Text)

Max Activating Token Index: 605

Text #1

Max Range: 3.0456. Min Range: -3.0456

Max Act: 3.0273. Min Act: -0.1700

Data Index: 6042396 (Open Web Text)

Max Activating Token Index: 188

Text #2

Max Range: 3.0456. Min Range: -3.0456

Max Act: 3.0456. Min Act: -0.1700

Data Index: 3903091 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.9716. Min Act: -0.1700

Data Index: 4602503 (Open Web Text)

Max Activating Token Index: 862

Text #4

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.9786. Min Act: -0.1700

Data Index: 4432435 (Open Web Text)

Max Activating Token Index: 454

Text #5

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.9353. Min Act: -0.1700

Data Index: 2013925 (Open Web Text)

Max Activating Token Index: 431

Text #6

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.9103. Min Act: -0.1700

Data Index: 8325684 (Open Web Text)

Max Activating Token Index: 834

Text #7

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.8780. Min Act: -0.1700

Data Index: 6579917 (Open Web Text)

Max Activating Token Index: 547

Text #8

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.8278. Min Act: -0.1700

Data Index: 7254568 (Open Web Text)

Max Activating Token Index: 323

Text #9

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.8377. Min Act: -0.1700

Data Index: 5855695 (Open Web Text)

Max Activating Token Index: 941

Text #10

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.8064. Min Act: -0.1700

Data Index: 6537024 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.8381. Min Act: -0.1700

Data Index: 4345596 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.7806. Min Act: -0.1700

Data Index: 7242334 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.8228. Min Act: -0.1700

Data Index: 6422511 (Open Web Text)

Max Activating Token Index: 588

Text #14

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.7893. Min Act: -0.1700

Data Index: 5027031 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.8055. Min Act: -0.1700

Data Index: 3987793 (Open Web Text)

Max Activating Token Index: 492

Text #16

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.7885. Min Act: -0.1700

Data Index: 8459653 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.7851. Min Act: -0.1700

Data Index: 2201675 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.7659. Min Act: -0.1700

Data Index: 8269947 (Open Web Text)

Max Activating Token Index: 662

Text #19

Max Range: 3.0456. Min Range: -3.0456

Max Act: 2.7426. Min Act: -0.1700

Data Index: 8729198 (Open Web Text)

Max Activating Token Index: 910