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

Dataset: Open Web Text

Neuron 689 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: 3.3451. Min Range: -3.3451

Max Act: 3.3451. Min Act: -0.1700

Data Index: 1408812 (Open Web Text)

Max Activating Token Index: 799

Text #1

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.3053. Min Act: -0.1700

Data Index: 836847 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.3078. Min Act: -0.1700

Data Index: 3425191 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.3117. Min Act: -0.1700

Data Index: 8215716 (Open Web Text)

Max Activating Token Index: 712

Text #4

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2974. Min Act: -0.1700

Data Index: 8481965 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2609. Min Act: -0.1700

Data Index: 8280676 (Open Web Text)

Max Activating Token Index: 536

Text #6

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2474. Min Act: -0.1700

Data Index: 1089288 (Open Web Text)

Max Activating Token Index: 546

Text #7

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2586. Min Act: -0.1700

Data Index: 5878985 (Open Web Text)

Max Activating Token Index: 889

Text #8

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2603. Min Act: -0.1700

Data Index: 4859416 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2491. Min Act: -0.1700

Data Index: 1931757 (Open Web Text)

Max Activating Token Index: 952

Text #10

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2463. Min Act: -0.1700

Data Index: 7405740 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.1969. Min Act: -0.1700

Data Index: 4374720 (Open Web Text)

Max Activating Token Index: 636

Text #12

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2116. Min Act: -0.1700

Data Index: 6028706 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2037. Min Act: -0.1700

Data Index: 5145513 (Open Web Text)

Max Activating Token Index: 850

Text #14

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2188. Min Act: -0.1700

Data Index: 8570303 (Open Web Text)

Max Activating Token Index: 627

Text #15

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.1854. Min Act: -0.1700

Data Index: 5767517 (Open Web Text)

Max Activating Token Index: 587

Text #16

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.2420. Min Act: -0.1700

Data Index: 1084394 (Open Web Text)

Max Activating Token Index: 991

Text #17

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.1477. Min Act: -0.1700

Data Index: 3271561 (Open Web Text)

Max Activating Token Index: 745

Text #18

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.1704. Min Act: -0.1700

Data Index: 2652132 (Open Web Text)

Max Activating Token Index: 894

Text #19

Max Range: 3.3451. Min Range: -3.3451

Max Act: 3.1908. Min Act: -0.1700

Data Index: 2960737 (Open Web Text)

Max Activating Token Index: 1023