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

Dataset: Open Web Text

Neuron 2621 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: 1.5924. Min Range: -1.5924

Max Act: 1.5924. Min Act: -0.1700

Data Index: 6477395 (Open Web Text)

Max Activating Token Index: 41

Text #1

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.5730. Min Act: -0.1700

Data Index: 4770704 (Open Web Text)

Max Activating Token Index: 59

Text #2

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.5462. Min Act: -0.1700

Data Index: 8723395 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.5100. Min Act: -0.1700

Data Index: 6916188 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.5164. Min Act: -0.1700

Data Index: 3098997 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4834. Min Act: -0.1700

Data Index: 4300895 (Open Web Text)

Max Activating Token Index: 286

Text #6

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4836. Min Act: -0.1700

Data Index: 5837141 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4726. Min Act: -0.1700

Data Index: 8547979 (Open Web Text)

Max Activating Token Index: 83

Text #8

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4740. Min Act: -0.1700

Data Index: 65318 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4712. Min Act: -0.1700

Data Index: 8764749 (Open Web Text)

Max Activating Token Index: 48

Text #10

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4723. Min Act: -0.1700

Data Index: 4430434 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4757. Min Act: -0.1700

Data Index: 2984017 (Open Web Text)

Max Activating Token Index: 472

Text #12

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4691. Min Act: -0.1700

Data Index: 5436762 (Open Web Text)

Max Activating Token Index: 307

Text #13

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4672. Min Act: -0.1700

Data Index: 7816048 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4703. Min Act: -0.1700

Data Index: 7538923 (Open Web Text)

Max Activating Token Index: 797

Text #15

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4684. Min Act: -0.1700

Data Index: 1243206 (Open Web Text)

Max Activating Token Index: 416

Text #16

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4770. Min Act: -0.1700

Data Index: 1971678 (Open Web Text)

Max Activating Token Index: 28

Text #17

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4635. Min Act: -0.1700

Data Index: 5799303 (Open Web Text)

Max Activating Token Index: 858

Text #18

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4539. Min Act: -0.1700

Data Index: 1704670 (Open Web Text)

Max Activating Token Index: 889

Text #19

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.4602. Min Act: -0.1700

Data Index: 350561 (Open Web Text)

Max Activating Token Index: 454