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

Dataset: Open Web Text

Neuron 163 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: 4.0543. Min Range: -4.0543

Max Act: 4.0543. Min Act: -0.1700

Data Index: 3995396 (Open Web Text)

Max Activating Token Index: 798

Text #1

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.9899. Min Act: -0.1700

Data Index: 3856811 (Open Web Text)

Max Activating Token Index: 850

Text #2

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.9518. Min Act: -0.1700

Data Index: 1134876 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8693. Min Act: -0.1700

Data Index: 3185304 (Open Web Text)

Max Activating Token Index: 781

Text #4

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.9064. Min Act: -0.1700

Data Index: 3594468 (Open Web Text)

Max Activating Token Index: 861

Text #5

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8893. Min Act: -0.1700

Data Index: 5492131 (Open Web Text)

Max Activating Token Index: 116

Text #6

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8925. Min Act: -0.1700

Data Index: 5109149 (Open Web Text)

Max Activating Token Index: 847

Text #7

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8758. Min Act: -0.1700

Data Index: 2892545 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8728. Min Act: -0.1700

Data Index: 8412984 (Open Web Text)

Max Activating Token Index: 784

Text #9

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8431. Min Act: -0.1700

Data Index: 3550957 (Open Web Text)

Max Activating Token Index: 190

Text #10

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8543. Min Act: -0.1700

Data Index: 5667472 (Open Web Text)

Max Activating Token Index: 923

Text #11

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8643. Min Act: -0.1700

Data Index: 2417864 (Open Web Text)

Max Activating Token Index: 323

Text #12

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8433. Min Act: -0.1700

Data Index: 1814781 (Open Web Text)

Max Activating Token Index: 638

Text #13

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8338. Min Act: -0.1700

Data Index: 5145129 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8605. Min Act: -0.1700

Data Index: 3347525 (Open Web Text)

Max Activating Token Index: 135

Text #15

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8596. Min Act: -0.1700

Data Index: 1939814 (Open Web Text)

Max Activating Token Index: 313

Text #16

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8621. Min Act: -0.1700

Data Index: 1730377 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8586. Min Act: -0.1700

Data Index: 8273707 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8237. Min Act: -0.1700

Data Index: 1444186 (Open Web Text)

Max Activating Token Index: 371

Text #19

Max Range: 4.0543. Min Range: -4.0543

Max Act: 3.8738. Min Act: -0.1700

Data Index: 6266770 (Open Web Text)

Max Activating Token Index: 288