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

Dataset: Open Web Text

Neuron 1407 in Layer 6

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: 3.5863. Min Range: -3.5863

Max Act: 3.5863. Min Act: -0.1700

Data Index: 2539607 (Open Web Text)

Max Activating Token Index: 531

Text #1

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.5747. Min Act: -0.1700

Data Index: 3387916 (Open Web Text)

Max Activating Token Index: 416

Text #2

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.5578. Min Act: -0.1700

Data Index: 5000096 (Open Web Text)

Max Activating Token Index: 432

Text #3

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.5283. Min Act: -0.1700

Data Index: 5352990 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.5427. Min Act: -0.1700

Data Index: 2884438 (Open Web Text)

Max Activating Token Index: 391

Text #5

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.5260. Min Act: -0.1700

Data Index: 559826 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.5113. Min Act: -0.1700

Data Index: 1747132 (Open Web Text)

Max Activating Token Index: 569

Text #7

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4995. Min Act: -0.1700

Data Index: 188685 (Open Web Text)

Max Activating Token Index: 805

Text #8

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.5073. Min Act: -0.1700

Data Index: 3654623 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4895. Min Act: -0.1700

Data Index: 5805174 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4914. Min Act: -0.1700

Data Index: 7981473 (Open Web Text)

Max Activating Token Index: 609

Text #11

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4818. Min Act: -0.1700

Data Index: 1481283 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4915. Min Act: -0.1700

Data Index: 8326953 (Open Web Text)

Max Activating Token Index: 770

Text #13

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4822. Min Act: -0.1700

Data Index: 481712 (Open Web Text)

Max Activating Token Index: 295

Text #14

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4633. Min Act: -0.1700

Data Index: 3421595 (Open Web Text)

Max Activating Token Index: 480

Text #15

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4637. Min Act: -0.1700

Data Index: 5523348 (Open Web Text)

Max Activating Token Index: 923

Text #16

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4651. Min Act: -0.1700

Data Index: 2020624 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4639. Min Act: -0.1700

Data Index: 4112435 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4445. Min Act: -0.1700

Data Index: 283520 (Open Web Text)

Max Activating Token Index: 521

Text #19

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.4522. Min Act: -0.1700

Data Index: 68772 (Open Web Text)

Max Activating Token Index: 351