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

Dataset: Open Web Text

Neuron 1794 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: 0.7099. Min Range: -0.7099

Max Act: 0.7099. Min Act: -0.1700

Data Index: 4388228 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.7060. Min Act: -0.1700

Data Index: 3695569 (Open Web Text)

Max Activating Token Index: 442

Text #2

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6917. Min Act: -0.1700

Data Index: 1115073 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6959. Min Act: -0.1700

Data Index: 4012437 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6942. Min Act: -0.1700

Data Index: 4766732 (Open Web Text)

Max Activating Token Index: 436

Text #5

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6947. Min Act: -0.1700

Data Index: 3816748 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6855. Min Act: -0.1700

Data Index: 5734765 (Open Web Text)

Max Activating Token Index: 441

Text #7

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6664. Min Act: -0.1700

Data Index: 6398777 (Open Web Text)

Max Activating Token Index: 449

Text #8

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6794. Min Act: -0.1700

Data Index: 5032188 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6741. Min Act: -0.1700

Data Index: 8285771 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6696. Min Act: -0.1700

Data Index: 6873861 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6648. Min Act: -0.1700

Data Index: 4344336 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6580. Min Act: -0.1700

Data Index: 1320024 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6600. Min Act: -0.1700

Data Index: 3535091 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6607. Min Act: -0.1700

Data Index: 4586512 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6548. Min Act: -0.1700

Data Index: 3443810 (Open Web Text)

Max Activating Token Index: 437

Text #16

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6497. Min Act: -0.1700

Data Index: 3008168 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6586. Min Act: -0.1700

Data Index: 2156523 (Open Web Text)

Max Activating Token Index: 415

Text #18

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6509. Min Act: -0.1700

Data Index: 4147335 (Open Web Text)

Max Activating Token Index: 450

Text #19

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6593. Min Act: -0.1700

Data Index: 5189002 (Open Web Text)

Max Activating Token Index: 435