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

Dataset: Open Web Text

Neuron 2747 in Layer 3

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: 4.6517. Min Range: -4.6517

Max Act: 4.6517. Min Act: -0.1700

Data Index: 6026381 (Open Web Text)

Max Activating Token Index: 551

Text #1

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.5784. Min Act: -0.1700

Data Index: 4779649 (Open Web Text)

Max Activating Token Index: 490

Text #2

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.4520. Min Act: -0.1700

Data Index: 8657208 (Open Web Text)

Max Activating Token Index: 609

Text #3

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.4754. Min Act: -0.1700

Data Index: 1919522 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.4368. Min Act: -0.1700

Data Index: 7096287 (Open Web Text)

Max Activating Token Index: 857

Text #5

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.4284. Min Act: -0.1700

Data Index: 4843398 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3964. Min Act: -0.1700

Data Index: 4738129 (Open Web Text)

Max Activating Token Index: 758

Text #7

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3793. Min Act: -0.1700

Data Index: 4784061 (Open Web Text)

Max Activating Token Index: 992

Text #8

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3837. Min Act: -0.1700

Data Index: 6921445 (Open Web Text)

Max Activating Token Index: 896

Text #9

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.4083. Min Act: -0.1700

Data Index: 649472 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3537. Min Act: -0.1700

Data Index: 476211 (Open Web Text)

Max Activating Token Index: 837

Text #11

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3646. Min Act: -0.1700

Data Index: 5032618 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3666. Min Act: -0.1700

Data Index: 6919995 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3658. Min Act: -0.1700

Data Index: 5772546 (Open Web Text)

Max Activating Token Index: 361

Text #14

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3718. Min Act: -0.1700

Data Index: 5336012 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3655. Min Act: -0.1700

Data Index: 3663489 (Open Web Text)

Max Activating Token Index: 942

Text #16

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3347. Min Act: -0.1700

Data Index: 4384466 (Open Web Text)

Max Activating Token Index: 133

Text #17

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.3275. Min Act: -0.1700

Data Index: 6548749 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.2801. Min Act: -0.1700

Data Index: 7663912 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 4.6517. Min Range: -4.6517

Max Act: 4.2899. Min Act: -0.1700

Data Index: 3663490 (Open Web Text)

Max Activating Token Index: 573