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

Dataset: Open Web Text

Neuron 1231 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: 4.1264. Min Range: -4.1264

Max Act: 4.1264. Min Act: -0.1700

Data Index: 6778306 (Open Web Text)

Max Activating Token Index: 990

Text #1

Max Range: 4.1264. Min Range: -4.1264

Max Act: 4.0732. Min Act: -0.1700

Data Index: 8757883 (Open Web Text)

Max Activating Token Index: 762

Text #2

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.9885. Min Act: -0.1700

Data Index: 736774 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.9122. Min Act: -0.1700

Data Index: 183868 (Open Web Text)

Max Activating Token Index: 255

Text #4

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.8920. Min Act: -0.1700

Data Index: 5472707 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.8903. Min Act: -0.1700

Data Index: 2743093 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.8648. Min Act: -0.1700

Data Index: 6258553 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.8534. Min Act: -0.1700

Data Index: 1142036 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.8693. Min Act: -0.1700

Data Index: 818075 (Open Web Text)

Max Activating Token Index: 828

Text #9

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.8104. Min Act: -0.1700

Data Index: 6495518 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.8279. Min Act: -0.1700

Data Index: 4779949 (Open Web Text)

Max Activating Token Index: 831

Text #11

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.8211. Min Act: -0.1700

Data Index: 7845623 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.7876. Min Act: -0.1700

Data Index: 7283757 (Open Web Text)

Max Activating Token Index: 393

Text #13

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.7826. Min Act: -0.1700

Data Index: 2995159 (Open Web Text)

Max Activating Token Index: 364

Text #14

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.7843. Min Act: -0.1700

Data Index: 5084491 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.7670. Min Act: -0.1700

Data Index: 4897427 (Open Web Text)

Max Activating Token Index: 574

Text #16

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.7711. Min Act: -0.1700

Data Index: 7200462 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.7492. Min Act: -0.1700

Data Index: 1376991 (Open Web Text)

Max Activating Token Index: 696

Text #18

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.7684. Min Act: -0.1700

Data Index: 4471821 (Open Web Text)

Max Activating Token Index: 594

Text #19

Max Range: 4.1264. Min Range: -4.1264

Max Act: 3.7885. Min Act: -0.1700

Data Index: 6297743 (Open Web Text)

Max Activating Token Index: 74