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

Dataset: Open Web Text

Neuron 659 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: 1.4696. Min Range: -1.4696

Max Act: 1.4696. Min Act: -0.1693

Data Index: 5576875 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3899. Min Act: -0.1698

Data Index: 5225857 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3834. Min Act: -0.1700

Data Index: 3964791 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3847. Min Act: -0.1692

Data Index: 2332126 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3911. Min Act: -0.1700

Data Index: 1803014 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3785. Min Act: -0.1700

Data Index: 6153124 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3700. Min Act: -0.1700

Data Index: 8137520 (Open Web Text)

Max Activating Token Index: 539

Text #7

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3675. Min Act: -0.1700

Data Index: 5358811 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3579. Min Act: -0.1700

Data Index: 8634011 (Open Web Text)

Max Activating Token Index: 810

Text #9

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3536. Min Act: -0.1700

Data Index: 6575237 (Open Web Text)

Max Activating Token Index: 144

Text #10

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3639. Min Act: -0.1698

Data Index: 4548675 (Open Web Text)

Max Activating Token Index: 385

Text #11

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3517. Min Act: -0.1700

Data Index: 4189450 (Open Web Text)

Max Activating Token Index: 488

Text #12

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3547. Min Act: -0.1700

Data Index: 4935137 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3468. Min Act: -0.1650

Data Index: 7785681 (Open Web Text)

Max Activating Token Index: 584

Text #14

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3570. Min Act: -0.1700

Data Index: 3938866 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3387. Min Act: -0.1700

Data Index: 8329145 (Open Web Text)

Max Activating Token Index: 465

Text #16

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3474. Min Act: -0.1700

Data Index: 7745331 (Open Web Text)

Max Activating Token Index: 565

Text #17

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3420. Min Act: -0.1700

Data Index: 4532382 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3444. Min Act: -0.1689

Data Index: 6153128 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.3454. Min Act: -0.1699

Data Index: 121278 (Open Web Text)

Max Activating Token Index: 18