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

Dataset: Open Web Text

Neuron 748 in Layer 5

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: 7.2704. Min Range: -7.2704

Max Act: 7.2704. Min Act: -0.1700

Data Index: 4363304 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.2192. Min Act: -0.1700

Data Index: 1040229 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.1805. Min Act: -0.1700

Data Index: 673960 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.1318. Min Act: -0.1700

Data Index: 6003566 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.1601. Min Act: -0.1700

Data Index: 1451451 (Open Web Text)

Max Activating Token Index: 658

Text #5

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.1596. Min Act: -0.1700

Data Index: 8171616 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.1359. Min Act: -0.1700

Data Index: 328176 (Open Web Text)

Max Activating Token Index: 560

Text #7

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.1451. Min Act: -0.1700

Data Index: 7467862 (Open Web Text)

Max Activating Token Index: 1015

Text #8

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.1027. Min Act: -0.1700

Data Index: 8074619 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.0954. Min Act: -0.1700

Data Index: 3213216 (Open Web Text)

Max Activating Token Index: 476

Text #10

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.0738. Min Act: -0.1700

Data Index: 1373582 (Open Web Text)

Max Activating Token Index: 933

Text #11

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.0737. Min Act: -0.1700

Data Index: 4237931 (Open Web Text)

Max Activating Token Index: 831

Text #12

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.0651. Min Act: -0.1700

Data Index: 7443478 (Open Web Text)

Max Activating Token Index: 423

Text #13

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.0379. Min Act: -0.1700

Data Index: 5314221 (Open Web Text)

Max Activating Token Index: 950

Text #14

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.0474. Min Act: -0.1700

Data Index: 3439945 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.0553. Min Act: -0.1700

Data Index: 2500584 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 7.2704. Min Range: -7.2704

Max Act: 7.0018. Min Act: -0.1700

Data Index: 4147748 (Open Web Text)

Max Activating Token Index: 953

Text #17

Max Range: 7.2704. Min Range: -7.2704

Max Act: 6.9557. Min Act: -0.1700

Data Index: 7031386 (Open Web Text)

Max Activating Token Index: 575

Text #18

Max Range: 7.2704. Min Range: -7.2704

Max Act: 6.9764. Min Act: -0.1700

Data Index: 7624557 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 7.2704. Min Range: -7.2704

Max Act: 6.9721. Min Act: -0.1700

Data Index: 8461223 (Open Web Text)

Max Activating Token Index: 450