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

Dataset: Open Web Text

Neuron 2218 in Layer 6

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: 4.1389. Min Range: -4.1389

Max Act: 4.1389. Min Act: -0.1700

Data Index: 1242557 (Open Web Text)

Max Activating Token Index: 723

Text #1

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0968. Min Act: -0.1700

Data Index: 6964151 (Open Web Text)

Max Activating Token Index: 207

Text #2

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0263. Min Act: -0.1695

Data Index: 3008964 (Open Web Text)

Max Activating Token Index: 869

Text #3

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0218. Min Act: -0.1700

Data Index: 721944 (Open Web Text)

Max Activating Token Index: 849

Text #4

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9921. Min Act: -0.1700

Data Index: 8758085 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0021. Min Act: -0.1700

Data Index: 8026673 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1253899 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9683. Min Act: -0.1700

Data Index: 5893148 (Open Web Text)

Max Activating Token Index: 750

Text #8

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9139. Min Act: -0.1700

Data Index: 4578794 (Open Web Text)

Max Activating Token Index: 682

Text #9

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9244. Min Act: -0.1700

Data Index: 4494589 (Open Web Text)

Max Activating Token Index: 300

Text #10

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9274. Min Act: -0.1700

Data Index: 2539079 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9287. Min Act: -0.1700

Data Index: 8414226 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9145. Min Act: -0.1700

Data Index: 1517109 (Open Web Text)

Max Activating Token Index: 749

Text #13

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.8888. Min Act: -0.1700

Data Index: 5797164 (Open Web Text)

Max Activating Token Index: 863

Text #14

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9232. Min Act: -0.1700

Data Index: 3008966 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9020. Min Act: -0.1700

Data Index: 3008961 (Open Web Text)

Max Activating Token Index: 891

Text #16

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9036. Min Act: -0.1700

Data Index: 2611594 (Open Web Text)

Max Activating Token Index: 356

Text #17

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.8701. Min Act: -0.1700

Data Index: 3943693 (Open Web Text)

Max Activating Token Index: 198

Text #18

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9022. Min Act: -0.1699

Data Index: 3008944 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.8612. Min Act: -0.1691

Data Index: 3008963 (Open Web Text)

Max Activating Token Index: 903