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

Dataset: Open Web Text

Neuron 443 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: 1.0959. Min Range: -1.0959

Max Act: 1.0959. Min Act: -0.1700

Data Index: 6144393 (Open Web Text)

Max Activating Token Index: 433

Text #1

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0753. Min Act: -0.1700

Data Index: 3344666 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0656. Min Act: -0.1700

Data Index: 260313 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0671. Min Act: -0.1700

Data Index: 6144386 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0524. Min Act: -0.1700

Data Index: 5945437 (Open Web Text)

Max Activating Token Index: 413

Text #5

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0607. Min Act: -0.1700

Data Index: 1304742 (Open Web Text)

Max Activating Token Index: 433

Text #6

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0507. Min Act: -0.1700

Data Index: 2621181 (Open Web Text)

Max Activating Token Index: 463

Text #7

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0465. Min Act: -0.1700

Data Index: 837478 (Open Web Text)

Max Activating Token Index: 441

Text #8

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0638. Min Act: -0.1700

Data Index: 1925264 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0490. Min Act: -0.1700

Data Index: 6144389 (Open Web Text)

Max Activating Token Index: 424

Text #10

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0610. Min Act: -0.1700

Data Index: 64180 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0436. Min Act: -0.1700

Data Index: 2075081 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0299. Min Act: -0.1700

Data Index: 1280146 (Open Web Text)

Max Activating Token Index: 436

Text #13

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0476. Min Act: -0.1700

Data Index: 492914 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0329. Min Act: -0.1700

Data Index: 3367426 (Open Web Text)

Max Activating Token Index: 438

Text #15

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0551. Min Act: -0.1700

Data Index: 7228328 (Open Web Text)

Max Activating Token Index: 460

Text #16

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0425. Min Act: -0.1700

Data Index: 564804 (Open Web Text)

Max Activating Token Index: 464

Text #17

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0372. Min Act: -0.1700

Data Index: 7454709 (Open Web Text)

Max Activating Token Index: 452

Text #18

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0411. Min Act: -0.1700

Data Index: 7741559 (Open Web Text)

Max Activating Token Index: 429

Text #19

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0473. Min Act: -0.1700

Data Index: 3180759 (Open Web Text)

Max Activating Token Index: 459