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

Dataset: Open Web Text

Neuron 988 in Layer 6

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: 3.2733. Min Range: -3.2733

Max Act: 3.2733. Min Act: -0.1700

Data Index: 1186534 (Open Web Text)

Max Activating Token Index: 482

Text #1

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.2496. Min Act: -0.1700

Data Index: 8473055 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.2149. Min Act: -0.1700

Data Index: 8272264 (Open Web Text)

Max Activating Token Index: 646

Text #3

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1712. Min Act: -0.1700

Data Index: 5524359 (Open Web Text)

Max Activating Token Index: 800

Text #4

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1639. Min Act: -0.1700

Data Index: 5546145 (Open Web Text)

Max Activating Token Index: 187

Text #5

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1633. Min Act: -0.1700

Data Index: 3555103 (Open Web Text)

Max Activating Token Index: 452

Text #6

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1507. Min Act: -0.1700

Data Index: 7032735 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1496. Min Act: -0.1700

Data Index: 1483254 (Open Web Text)

Max Activating Token Index: 124

Text #8

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1369. Min Act: -0.1700

Data Index: 559415 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1575. Min Act: -0.1700

Data Index: 5769571 (Open Web Text)

Max Activating Token Index: 203

Text #10

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1401. Min Act: -0.1700

Data Index: 3881377 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1557. Min Act: -0.1700

Data Index: 372328 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1428. Min Act: -0.1700

Data Index: 4269543 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1274. Min Act: -0.1700

Data Index: 919605 (Open Web Text)

Max Activating Token Index: 850

Text #14

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1245. Min Act: -0.1700

Data Index: 756088 (Open Web Text)

Max Activating Token Index: 723

Text #15

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1355. Min Act: -0.1700

Data Index: 4400427 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1153. Min Act: -0.1700

Data Index: 6173982 (Open Web Text)

Max Activating Token Index: 761

Text #17

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1349. Min Act: -0.1700

Data Index: 2963625 (Open Web Text)

Max Activating Token Index: 569

Text #18

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.1134. Min Act: -0.1700

Data Index: 549013 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 3.2733. Min Range: -3.2733

Max Act: 3.0972. Min Act: -0.1700

Data Index: 2360384 (Open Web Text)

Max Activating Token Index: 423