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

Dataset: Open Web Text

Neuron 519 in Layer 6

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: 4.6069. Min Range: -4.6069

Max Act: 4.6069. Min Act: -0.1700

Data Index: 1785782 (Open Web Text)

Max Activating Token Index: 417

Text #1

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.5092. Min Act: -0.1700

Data Index: 145558 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.5117. Min Act: -0.1700

Data Index: 1785786 (Open Web Text)

Max Activating Token Index: 324

Text #3

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.4521. Min Act: -0.1700

Data Index: 5878848 (Open Web Text)

Max Activating Token Index: 529

Text #4

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.4396. Min Act: -0.1700

Data Index: 7060789 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.4077. Min Act: -0.1700

Data Index: 1785779 (Open Web Text)

Max Activating Token Index: 395

Text #6

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.4084. Min Act: -0.1700

Data Index: 145557 (Open Web Text)

Max Activating Token Index: 736

Text #7

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.3102. Min Act: -0.1700

Data Index: 1785785 (Open Web Text)

Max Activating Token Index: 775

Text #8

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.3368. Min Act: -0.1700

Data Index: 1785787 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2995. Min Act: -0.1700

Data Index: 4437686 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2639. Min Act: -0.1700

Data Index: 1785778 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2920. Min Act: -0.1700

Data Index: 7060798 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2639. Min Act: -0.1700

Data Index: 1785788 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2358. Min Act: -0.1700

Data Index: 7060794 (Open Web Text)

Max Activating Token Index: 524

Text #14

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2648. Min Act: -0.1700

Data Index: 1785781 (Open Web Text)

Max Activating Token Index: 213

Text #15

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2631. Min Act: -0.1700

Data Index: 4027814 (Open Web Text)

Max Activating Token Index: 369

Text #16

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2838. Min Act: -0.1700

Data Index: 7791039 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2463. Min Act: -0.1700

Data Index: 7060797 (Open Web Text)

Max Activating Token Index: 376

Text #18

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2380. Min Act: -0.1700

Data Index: 7060790 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 4.6069. Min Range: -4.6069

Max Act: 4.2325. Min Act: -0.1700

Data Index: 1785784 (Open Web Text)

Max Activating Token Index: 556