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

Dataset: Open Web Text

Neuron 5 in Layer 2

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: 4.4820. Min Range: -4.4820

Max Act: 4.4820. Min Act: -0.1700

Data Index: 1941823 (Open Web Text)

Max Activating Token Index: 377

Text #1

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.4795. Min Act: -0.1700

Data Index: 3354341 (Open Web Text)

Max Activating Token Index: 405

Text #2

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.4549. Min Act: -0.1700

Data Index: 4996548 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.4477. Min Act: -0.1700

Data Index: 1703435 (Open Web Text)

Max Activating Token Index: 813

Text #4

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.4052. Min Act: -0.1700

Data Index: 5048926 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3893. Min Act: -0.1700

Data Index: 1532678 (Open Web Text)

Max Activating Token Index: 238

Text #6

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3894. Min Act: -0.1700

Data Index: 117354 (Open Web Text)

Max Activating Token Index: 755

Text #7

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.4084. Min Act: -0.1700

Data Index: 6329893 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3796. Min Act: -0.1700

Data Index: 6145333 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3688. Min Act: -0.1700

Data Index: 954702 (Open Web Text)

Max Activating Token Index: 586

Text #10

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3770. Min Act: -0.1700

Data Index: 7768125 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3864. Min Act: -0.1700

Data Index: 3141912 (Open Web Text)

Max Activating Token Index: 457

Text #12

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3842. Min Act: -0.1700

Data Index: 1462567 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3784. Min Act: -0.1700

Data Index: 5002625 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3812. Min Act: -0.1700

Data Index: 6840321 (Open Web Text)

Max Activating Token Index: 563

Text #15

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3558. Min Act: -0.1700

Data Index: 6965039 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3417. Min Act: -0.1700

Data Index: 8363584 (Open Web Text)

Max Activating Token Index: 757

Text #17

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3559. Min Act: -0.1700

Data Index: 3835619 (Open Web Text)

Max Activating Token Index: 94

Text #18

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3612. Min Act: -0.1700

Data Index: 4207782 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 4.4820. Min Range: -4.4820

Max Act: 4.3410. Min Act: -0.1700

Data Index: 6467627 (Open Web Text)

Max Activating Token Index: 47