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

Dataset: Open Web Text

Neuron 1470 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: 3.3463. Min Range: -3.3463

Max Act: 3.3463. Min Act: -0.1700

Data Index: 4193813 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 3.3463. Min Range: -3.3463

Max Act: 3.2460. Min Act: -0.1700

Data Index: 5790763 (Open Web Text)

Max Activating Token Index: 883

Text #2

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.5666. Min Act: -0.1700

Data Index: 8756019 (Open Web Text)

Max Activating Token Index: 687

Text #3

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.5630. Min Act: -0.1700

Data Index: 7448679 (Open Web Text)

Max Activating Token Index: 217

Text #4

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.5410. Min Act: -0.1700

Data Index: 7427476 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.5064. Min Act: -0.1700

Data Index: 6483895 (Open Web Text)

Max Activating Token Index: 957

Text #6

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4997. Min Act: -0.1700

Data Index: 524367 (Open Web Text)

Max Activating Token Index: 453

Text #7

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4899. Min Act: -0.1700

Data Index: 4210687 (Open Web Text)

Max Activating Token Index: 353

Text #8

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4827. Min Act: -0.1700

Data Index: 4628822 (Open Web Text)

Max Activating Token Index: 505

Text #9

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4566. Min Act: -0.1700

Data Index: 825451 (Open Web Text)

Max Activating Token Index: 175

Text #10

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4741. Min Act: -0.1700

Data Index: 4779954 (Open Web Text)

Max Activating Token Index: 822

Text #11

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4507. Min Act: -0.1700

Data Index: 4779956 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4350. Min Act: -0.1700

Data Index: 6428917 (Open Web Text)

Max Activating Token Index: 373

Text #13

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4535. Min Act: -0.1700

Data Index: 986243 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4520. Min Act: -0.1700

Data Index: 4237103 (Open Web Text)

Max Activating Token Index: 416

Text #15

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4536. Min Act: -0.1700

Data Index: 3759388 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4631. Min Act: -0.1700

Data Index: 3539478 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4407. Min Act: -0.1700

Data Index: 4431663 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4484. Min Act: -0.1700

Data Index: 6188192 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 3.3463. Min Range: -3.3463

Max Act: 2.4605. Min Act: -0.1700

Data Index: 591032 (Open Web Text)

Max Activating Token Index: 388