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

Dataset: Open Web Text

Neuron 1110 in Layer 0

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: 0.7798. Min Range: -0.7798

Max Act: 0.7798. Min Act: -0.1621

Data Index: 6861454 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7694. Min Act: -0.1615

Data Index: 7264042 (Open Web Text)

Max Activating Token Index: 578

Text #2

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7599. Min Act: -0.1631

Data Index: 5886200 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7630. Min Act: -0.1648

Data Index: 8793927 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7511. Min Act: -0.1659

Data Index: 6733058 (Open Web Text)

Max Activating Token Index: 665

Text #5

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7485. Min Act: -0.1581

Data Index: 68866 (Open Web Text)

Max Activating Token Index: 550

Text #6

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7443. Min Act: -0.1611

Data Index: 3002421 (Open Web Text)

Max Activating Token Index: 683

Text #7

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7422. Min Act: -0.1678

Data Index: 5591234 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7394. Min Act: -0.1366

Data Index: 5832300 (Open Web Text)

Max Activating Token Index: 793

Text #9

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7319. Min Act: -0.1622

Data Index: 3041335 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7331. Min Act: -0.1642

Data Index: 8438404 (Open Web Text)

Max Activating Token Index: 618

Text #11

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7363. Min Act: -0.1674

Data Index: 8204857 (Open Web Text)

Max Activating Token Index: 669

Text #12

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7360. Min Act: -0.1572

Data Index: 175213 (Open Web Text)

Max Activating Token Index: 607

Text #13

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7343. Min Act: -0.1675

Data Index: 7570683 (Open Web Text)

Max Activating Token Index: 645

Text #14

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7326. Min Act: -0.1673

Data Index: 7909880 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7314. Min Act: -0.1679

Data Index: 6153315 (Open Web Text)

Max Activating Token Index: 603

Text #16

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7291. Min Act: -0.1695

Data Index: 8111403 (Open Web Text)

Max Activating Token Index: 595

Text #17

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7327. Min Act: -0.1621

Data Index: 7315473 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7304. Min Act: -0.1410

Data Index: 4865073 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7277. Min Act: -0.1620

Data Index: 5738897 (Open Web Text)

Max Activating Token Index: 631