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

Dataset: Open Web Text

Neuron 984 in Layer 3

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: 3.2557. Min Range: -3.2557

Max Act: 3.2557. Min Act: -0.1700

Data Index: 32258 (Open Web Text)

Max Activating Token Index: 518

Text #1

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2114. Min Act: -0.1700

Data Index: 8528841 (Open Web Text)

Max Activating Token Index: 500

Text #2

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2303. Min Act: -0.1700

Data Index: 322710 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2469. Min Act: -0.1700

Data Index: 8404683 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1902. Min Act: -0.1700

Data Index: 5668990 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2289. Min Act: -0.1700

Data Index: 6071105 (Open Web Text)

Max Activating Token Index: 473

Text #6

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2153. Min Act: -0.1700

Data Index: 5550421 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2193. Min Act: -0.1700

Data Index: 5655445 (Open Web Text)

Max Activating Token Index: 378

Text #8

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1571. Min Act: -0.1700

Data Index: 7052312 (Open Web Text)

Max Activating Token Index: 454

Text #9

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1694. Min Act: -0.1700

Data Index: 2416489 (Open Web Text)

Max Activating Token Index: 504

Text #10

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1551. Min Act: -0.1700

Data Index: 8776465 (Open Web Text)

Max Activating Token Index: 246

Text #11

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1756. Min Act: -0.1700

Data Index: 8436882 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1881. Min Act: -0.1700

Data Index: 1919306 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1729. Min Act: -0.1700

Data Index: 4761553 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1607. Min Act: -0.1700

Data Index: 7452374 (Open Web Text)

Max Activating Token Index: 573

Text #15

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1772. Min Act: -0.1700

Data Index: 6150623 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1652. Min Act: -0.1700

Data Index: 1088374 (Open Web Text)

Max Activating Token Index: 380

Text #17

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1701. Min Act: -0.1700

Data Index: 5800713 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1317. Min Act: -0.1700

Data Index: 2024538 (Open Web Text)

Max Activating Token Index: 575

Text #19

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1702. Min Act: -0.1700

Data Index: 4826536 (Open Web Text)

Max Activating Token Index: 466