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

Dataset: Open Web Text

Neuron 102 in Layer 1

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: 3.5605. Min Range: -3.5605

Max Act: 3.5533. Min Act: -0.1700

Data Index: 1037571 (Open Web Text)

Max Activating Token Index: 189

Text #1

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.5605. Min Act: -0.1700

Data Index: 5158100 (Open Web Text)

Max Activating Token Index: 447

Text #2

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.5087. Min Act: -0.1700

Data Index: 4892626 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.5135. Min Act: -0.1700

Data Index: 8755314 (Open Web Text)

Max Activating Token Index: 207

Text #4

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.5358. Min Act: -0.1700

Data Index: 6785425 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.5146. Min Act: -0.1700

Data Index: 6766426 (Open Web Text)

Max Activating Token Index: 714

Text #6

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4936. Min Act: -0.1700

Data Index: 5993725 (Open Web Text)

Max Activating Token Index: 627

Text #7

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4875. Min Act: -0.1700

Data Index: 714190 (Open Web Text)

Max Activating Token Index: 738

Text #8

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.5007. Min Act: -0.1700

Data Index: 7735085 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.5007. Min Act: -0.1700

Data Index: 7446415 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4853. Min Act: -0.1700

Data Index: 2697099 (Open Web Text)

Max Activating Token Index: 666

Text #11

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4871. Min Act: -0.1700

Data Index: 6564818 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4831. Min Act: -0.1700

Data Index: 8212929 (Open Web Text)

Max Activating Token Index: 585

Text #13

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.5007. Min Act: -0.1700

Data Index: 4259906 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1174206 (Open Web Text)

Max Activating Token Index: 357

Text #15

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4689. Min Act: -0.1700

Data Index: 5713583 (Open Web Text)

Max Activating Token Index: 739

Text #16

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4948. Min Act: -0.1700

Data Index: 5975858 (Open Web Text)

Max Activating Token Index: 841

Text #17

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4789. Min Act: -0.1700

Data Index: 6014411 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4579. Min Act: -0.1700

Data Index: 5149086 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 3.5605. Min Range: -3.5605

Max Act: 3.4504. Min Act: -0.1700

Data Index: 7168342 (Open Web Text)

Max Activating Token Index: 4