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

Dataset: Open Web Text

Neuron 877 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: 3.4068. Min Range: -3.4068

Max Act: 3.4068. Min Act: -0.1700

Data Index: 3473984 (Open Web Text)

Max Activating Token Index: 879

Text #1

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3312. Min Act: -0.1700

Data Index: 5492418 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2974. Min Act: -0.1700

Data Index: 2470589 (Open Web Text)

Max Activating Token Index: 603

Text #3

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2854. Min Act: -0.1700

Data Index: 29782 (Open Web Text)

Max Activating Token Index: 828

Text #4

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2443. Min Act: -0.1700

Data Index: 4246734 (Open Web Text)

Max Activating Token Index: 478

Text #5

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2379. Min Act: -0.1700

Data Index: 6263843 (Open Web Text)

Max Activating Token Index: 803

Text #6

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2502. Min Act: -0.1700

Data Index: 2836234 (Open Web Text)

Max Activating Token Index: 581

Text #7

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2325. Min Act: -0.1700

Data Index: 6634465 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2488. Min Act: -0.1700

Data Index: 5844757 (Open Web Text)

Max Activating Token Index: 567

Text #9

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2501. Min Act: -0.1700

Data Index: 7273810 (Open Web Text)

Max Activating Token Index: 519

Text #10

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2419. Min Act: -0.1700

Data Index: 8642961 (Open Web Text)

Max Activating Token Index: 840

Text #11

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2115. Min Act: -0.1700

Data Index: 4737494 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2079. Min Act: -0.1700

Data Index: 7471806 (Open Web Text)

Max Activating Token Index: 493

Text #13

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1917024 (Open Web Text)

Max Activating Token Index: 670

Text #14

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1699. Min Act: -0.1700

Data Index: 480245 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1833. Min Act: -0.1700

Data Index: 3839461 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1796. Min Act: -0.1700

Data Index: 2818395 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1891. Min Act: -0.1700

Data Index: 5972988 (Open Web Text)

Max Activating Token Index: 934

Text #18

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1684. Min Act: -0.1700

Data Index: 864949 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1622. Min Act: -0.1700

Data Index: 4807658 (Open Web Text)

Max Activating Token Index: 711