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

Dataset: Open Web Text

Neuron 2925 in Layer 4

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: 3.7343. Min Range: -3.7343

Max Act: 3.7343. Min Act: -0.1700

Data Index: 2794438 (Open Web Text)

Max Activating Token Index: 689

Text #1

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7145. Min Act: -0.1700

Data Index: 910582 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7073. Min Act: -0.1700

Data Index: 8493226 (Open Web Text)

Max Activating Token Index: 428

Text #3

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7161. Min Act: -0.1700

Data Index: 2828798 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7052. Min Act: -0.1700

Data Index: 5758475 (Open Web Text)

Max Activating Token Index: 518

Text #5

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7123. Min Act: -0.1700

Data Index: 4602226 (Open Web Text)

Max Activating Token Index: 432

Text #6

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6611. Min Act: -0.1700

Data Index: 639360 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6676. Min Act: -0.1700

Data Index: 5763846 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6634. Min Act: -0.1700

Data Index: 1032460 (Open Web Text)

Max Activating Token Index: 370

Text #9

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6676. Min Act: -0.1700

Data Index: 5748645 (Open Web Text)

Max Activating Token Index: 784

Text #10

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6840. Min Act: -0.1700

Data Index: 3241642 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6694. Min Act: -0.1700

Data Index: 7694902 (Open Web Text)

Max Activating Token Index: 249

Text #12

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6657. Min Act: -0.1700

Data Index: 248271 (Open Web Text)

Max Activating Token Index: 275

Text #13

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6452. Min Act: -0.1700

Data Index: 3877354 (Open Web Text)

Max Activating Token Index: 361

Text #14

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6262. Min Act: -0.1700

Data Index: 3579341 (Open Web Text)

Max Activating Token Index: 242

Text #15

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6460. Min Act: -0.1700

Data Index: 6163482 (Open Web Text)

Max Activating Token Index: 886

Text #16

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6286. Min Act: -0.1700

Data Index: 6016852 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6154. Min Act: -0.1700

Data Index: 5947502 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6513. Min Act: -0.1700

Data Index: 3976272 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6198. Min Act: -0.1700

Data Index: 2462995 (Open Web Text)

Max Activating Token Index: 553