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

Dataset: Open Web Text

Neuron 1593 in Layer 3

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: 4.2149. Min Range: -4.2149

Max Act: 4.1397. Min Act: -0.1700

Data Index: 1267090 (Open Web Text)

Max Activating Token Index: 484

Text #1

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1582. Min Act: -0.1700

Data Index: 2013429 (Open Web Text)

Max Activating Token Index: 313

Text #2

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1457. Min Act: -0.1697

Data Index: 5133315 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1759. Min Act: -0.1700

Data Index: 8626713 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1637. Min Act: -0.1699

Data Index: 6910607 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1429. Min Act: -0.1698

Data Index: 7951297 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1598. Min Act: -0.1700

Data Index: 2401297 (Open Web Text)

Max Activating Token Index: 232

Text #7

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.2149. Min Act: -0.1700

Data Index: 7279324 (Open Web Text)

Max Activating Token Index: 480

Text #8

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.0779. Min Act: -0.1700

Data Index: 6952430 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1279. Min Act: -0.1700

Data Index: 3618972 (Open Web Text)

Max Activating Token Index: 641

Text #10

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1130. Min Act: -0.1698

Data Index: 1678489 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.0963. Min Act: -0.1700

Data Index: 4283617 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.0478. Min Act: -0.1700

Data Index: 8078334 (Open Web Text)

Max Activating Token Index: 436

Text #13

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.0919. Min Act: -0.1700

Data Index: 7487591 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.2149. Min Range: -4.2149

Max Act: 3.9592. Min Act: -0.1700

Data Index: 1018148 (Open Web Text)

Max Activating Token Index: 898

Text #15

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.0308. Min Act: -0.1700

Data Index: 7542632 (Open Web Text)

Max Activating Token Index: 227

Text #16

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.0908. Min Act: -0.1700

Data Index: 2267922 (Open Web Text)

Max Activating Token Index: 1002

Text #17

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.0506. Min Act: -0.1700

Data Index: 8077227 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.0805. Min Act: -0.1700

Data Index: 2046696 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 4.2149. Min Range: -4.2149

Max Act: 4.1193. Min Act: -0.1700

Data Index: 3126612 (Open Web Text)

Max Activating Token Index: 960