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

Dataset: Open Web Text

Neuron 648 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: 3.6844. Min Range: -3.6844

Max Act: 3.6844. Min Act: -0.1700

Data Index: 7100454 (Open Web Text)

Max Activating Token Index: 945

Text #1

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6293. Min Act: -0.1700

Data Index: 619287 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6335. Min Act: -0.1700

Data Index: 8327829 (Open Web Text)

Max Activating Token Index: 313

Text #3

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6319. Min Act: -0.1700

Data Index: 6556483 (Open Web Text)

Max Activating Token Index: 411

Text #4

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6282. Min Act: -0.1700

Data Index: 4363622 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6261. Min Act: -0.1700

Data Index: 3918505 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6209. Min Act: -0.1700

Data Index: 4886255 (Open Web Text)

Max Activating Token Index: 997

Text #7

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6209. Min Act: -0.1700

Data Index: 2046046 (Open Web Text)

Max Activating Token Index: 894

Text #8

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5839. Min Act: -0.1700

Data Index: 3697267 (Open Web Text)

Max Activating Token Index: 554

Text #9

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5751. Min Act: -0.1700

Data Index: 7057220 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6034. Min Act: -0.1700

Data Index: 2337433 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5717. Min Act: -0.1700

Data Index: 3081911 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5760. Min Act: -0.1700

Data Index: 256082 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5992. Min Act: -0.1700

Data Index: 8414270 (Open Web Text)

Max Activating Token Index: 392

Text #14

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6271. Min Act: -0.1700

Data Index: 4320159 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5772. Min Act: -0.1700

Data Index: 7029071 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5629. Min Act: -0.1700

Data Index: 6337960 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5628. Min Act: -0.1700

Data Index: 3642276 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5670. Min Act: -0.1700

Data Index: 4880217 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5798. Min Act: -0.1700

Data Index: 4794851 (Open Web Text)

Max Activating Token Index: 432