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

Dataset: Open Web Text

Neuron 1456 in Layer 2

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: 5.5666. Min Range: -5.5666

Max Act: 5.5613. Min Act: -0.1700

Data Index: 702004 (Open Web Text)

Max Activating Token Index: 889

Text #1

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5638. Min Act: -0.1700

Data Index: 952474 (Open Web Text)

Max Activating Token Index: 606

Text #2

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5666. Min Act: -0.1700

Data Index: 839749 (Open Web Text)

Max Activating Token Index: 934

Text #3

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4816. Min Act: -0.1700

Data Index: 8433442 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5075. Min Act: -0.1700

Data Index: 4425792 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4863. Min Act: -0.1700

Data Index: 3946184 (Open Web Text)

Max Activating Token Index: 1000

Text #6

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5309. Min Act: -0.1700

Data Index: 6872175 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4947. Min Act: -0.1697

Data Index: 4616220 (Open Web Text)

Max Activating Token Index: 386

Text #8

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5254. Min Act: -0.1700

Data Index: 4514520 (Open Web Text)

Max Activating Token Index: 720

Text #9

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5144. Min Act: -0.1700

Data Index: 2307302 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.5017. Min Act: -0.1699

Data Index: 1309137 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4504. Min Act: -0.1700

Data Index: 6769868 (Open Web Text)

Max Activating Token Index: 800

Text #12

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4841. Min Act: -0.1700

Data Index: 184088 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4411. Min Act: -0.1699

Data Index: 2323399 (Open Web Text)

Max Activating Token Index: 787

Text #14

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4408. Min Act: -0.1700

Data Index: 1256042 (Open Web Text)

Max Activating Token Index: 772

Text #15

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4711. Min Act: -0.1700

Data Index: 6616837 (Open Web Text)

Max Activating Token Index: 539

Text #16

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4218. Min Act: -0.1700

Data Index: 4829275 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4232. Min Act: -0.1700

Data Index: 7069946 (Open Web Text)

Max Activating Token Index: 345

Text #18

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4041. Min Act: -0.1700

Data Index: 2886795 (Open Web Text)

Max Activating Token Index: 843

Text #19

Max Range: 5.5666. Min Range: -5.5666

Max Act: 5.4174. Min Act: -0.1700

Data Index: 4236722 (Open Web Text)

Max Activating Token Index: 449