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

Dataset: Open Web Text

Neuron 493 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: 5.1406. Min Range: -5.1406

Max Act: 5.1406. Min Act: -0.1700

Data Index: 6591776 (Open Web Text)

Max Activating Token Index: 518

Text #1

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.1364. Min Act: -0.1700

Data Index: 3028906 (Open Web Text)

Max Activating Token Index: 414

Text #2

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.1276. Min Act: -0.1700

Data Index: 7449949 (Open Web Text)

Max Activating Token Index: 722

Text #3

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.1007. Min Act: -0.1700

Data Index: 3657172 (Open Web Text)

Max Activating Token Index: 453

Text #4

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0993. Min Act: -0.1700

Data Index: 3559564 (Open Web Text)

Max Activating Token Index: 308

Text #5

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0959. Min Act: -0.1700

Data Index: 3223404 (Open Web Text)

Max Activating Token Index: 29

Text #6

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.1263. Min Act: -0.1700

Data Index: 6950837 (Open Web Text)

Max Activating Token Index: 297

Text #7

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0718. Min Act: -0.1700

Data Index: 2746267 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0616. Min Act: -0.1700

Data Index: 3187558 (Open Web Text)

Max Activating Token Index: 343

Text #9

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0868. Min Act: -0.1700

Data Index: 2305279 (Open Web Text)

Max Activating Token Index: 430

Text #10

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0615. Min Act: -0.1700

Data Index: 7047293 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0950. Min Act: -0.1700

Data Index: 6954047 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0866. Min Act: -0.1700

Data Index: 5932650 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0878. Min Act: -0.1700

Data Index: 2463606 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0657. Min Act: -0.1700

Data Index: 3696769 (Open Web Text)

Max Activating Token Index: 938

Text #15

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0640. Min Act: -0.1700

Data Index: 1784177 (Open Web Text)

Max Activating Token Index: 51

Text #16

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0617. Min Act: -0.1700

Data Index: 1794525 (Open Web Text)

Max Activating Token Index: 90

Text #17

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0448. Min Act: -0.1700

Data Index: 1889290 (Open Web Text)

Max Activating Token Index: 338

Text #18

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0527. Min Act: -0.1700

Data Index: 1951712 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 5.1406. Min Range: -5.1406

Max Act: 5.0536. Min Act: -0.1700

Data Index: 1957933 (Open Web Text)

Max Activating Token Index: 549