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

Dataset: Open Web Text

Neuron 2659 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: 1.9368. Min Range: -1.9368

Max Act: 1.9368. Min Act: -0.1700

Data Index: 5217898 (Open Web Text)

Max Activating Token Index: 508

Text #1

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.9256. Min Act: -0.1700

Data Index: 6847956 (Open Web Text)

Max Activating Token Index: 571

Text #2

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.9291. Min Act: -0.1700

Data Index: 2639138 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8901. Min Act: -0.1700

Data Index: 62564 (Open Web Text)

Max Activating Token Index: 326

Text #4

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.9032. Min Act: -0.1697

Data Index: 8389407 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8909. Min Act: -0.1668

Data Index: 3898509 (Open Web Text)

Max Activating Token Index: 392

Text #6

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8886. Min Act: -0.1699

Data Index: 1955708 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8847. Min Act: -0.1699

Data Index: 2428917 (Open Web Text)

Max Activating Token Index: 355

Text #8

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8816. Min Act: -0.1700

Data Index: 4357525 (Open Web Text)

Max Activating Token Index: 551

Text #9

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8662. Min Act: -0.1691

Data Index: 2214876 (Open Web Text)

Max Activating Token Index: 974

Text #10

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8717. Min Act: -0.1700

Data Index: 5135583 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8651. Min Act: -0.1694

Data Index: 1265527 (Open Web Text)

Max Activating Token Index: 191

Text #12

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8581. Min Act: -0.1698

Data Index: 8673148 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8545. Min Act: -0.1700

Data Index: 1964111 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8580. Min Act: -0.1700

Data Index: 3086032 (Open Web Text)

Max Activating Token Index: 734

Text #15

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8597. Min Act: -0.1700

Data Index: 8143763 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8417. Min Act: -0.1700

Data Index: 1353687 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8461. Min Act: -0.1700

Data Index: 7365880 (Open Web Text)

Max Activating Token Index: 611

Text #18

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8368. Min Act: -0.1699

Data Index: 1447894 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 1.9368. Min Range: -1.9368

Max Act: 1.8430. Min Act: -0.1700

Data Index: 4162728 (Open Web Text)

Max Activating Token Index: 405