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

Dataset: Open Web Text

Neuron 2275 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: 1.5531. Min Range: -1.5531

Max Act: 1.5531. Min Act: -0.1700

Data Index: 7400645 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4901. Min Act: -0.1700

Data Index: 3965087 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.5083. Min Act: -0.1697

Data Index: 3246936 (Open Web Text)

Max Activating Token Index: 761

Text #3

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4922. Min Act: -0.1694

Data Index: 5549657 (Open Web Text)

Max Activating Token Index: 614

Text #4

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4809. Min Act: -0.1700

Data Index: 1870867 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4765. Min Act: -0.1696

Data Index: 7907079 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4738. Min Act: -0.1699

Data Index: 937666 (Open Web Text)

Max Activating Token Index: 906

Text #7

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4595. Min Act: -0.1700

Data Index: 401659 (Open Web Text)

Max Activating Token Index: 705

Text #8

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4688. Min Act: -0.1688

Data Index: 4680313 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4499. Min Act: -0.1690

Data Index: 2025416 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4499. Min Act: -0.1693

Data Index: 8490381 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4439. Min Act: -0.1700

Data Index: 7547890 (Open Web Text)

Max Activating Token Index: 344

Text #12

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4475. Min Act: -0.1700

Data Index: 4189904 (Open Web Text)

Max Activating Token Index: 677

Text #13

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4377. Min Act: -0.1700

Data Index: 7294100 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4440. Min Act: -0.1698

Data Index: 937664 (Open Web Text)

Max Activating Token Index: 338

Text #15

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4355. Min Act: -0.1700

Data Index: 210858 (Open Web Text)

Max Activating Token Index: 430

Text #16

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4399. Min Act: -0.1700

Data Index: 5937406 (Open Web Text)

Max Activating Token Index: 583

Text #17

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4380. Min Act: -0.1676

Data Index: 7435351 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4386. Min Act: -0.1680

Data Index: 2981278 (Open Web Text)

Max Activating Token Index: 689

Text #19

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.4291. Min Act: -0.1695

Data Index: 6095350 (Open Web Text)

Max Activating Token Index: 5