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

Dataset: Open Web Text

Neuron 372 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: 3.3291. Min Range: -3.3291

Max Act: 3.3291. Min Act: -0.1700

Data Index: 2871542 (Open Web Text)

Max Activating Token Index: 727

Text #1

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.2573. Min Act: -0.1700

Data Index: 4093250 (Open Web Text)

Max Activating Token Index: 329

Text #2

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.2364. Min Act: -0.1700

Data Index: 2375460 (Open Web Text)

Max Activating Token Index: 242

Text #3

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.2059. Min Act: -0.1700

Data Index: 828218 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.2367. Min Act: -0.1700

Data Index: 8732228 (Open Web Text)

Max Activating Token Index: 341

Text #5

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.2334. Min Act: -0.1700

Data Index: 4688108 (Open Web Text)

Max Activating Token Index: 910

Text #6

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.2351. Min Act: -0.1700

Data Index: 2094834 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.2153. Min Act: -0.1700

Data Index: 5889097 (Open Web Text)

Max Activating Token Index: 392

Text #8

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1947. Min Act: -0.1700

Data Index: 6595900 (Open Web Text)

Max Activating Token Index: 495

Text #9

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1996. Min Act: -0.1700

Data Index: 7143388 (Open Web Text)

Max Activating Token Index: 653

Text #10

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1962. Min Act: -0.1700

Data Index: 3026279 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1642. Min Act: -0.1700

Data Index: 7424239 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1805. Min Act: -0.1700

Data Index: 6564667 (Open Web Text)

Max Activating Token Index: 705

Text #13

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1690. Min Act: -0.1700

Data Index: 7832887 (Open Web Text)

Max Activating Token Index: 501

Text #14

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1692. Min Act: -0.1700

Data Index: 6185439 (Open Web Text)

Max Activating Token Index: 492

Text #15

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1567. Min Act: -0.1700

Data Index: 5643642 (Open Web Text)

Max Activating Token Index: 887

Text #16

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1691. Min Act: -0.1700

Data Index: 5588992 (Open Web Text)

Max Activating Token Index: 945

Text #17

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1466. Min Act: -0.1700

Data Index: 5007737 (Open Web Text)

Max Activating Token Index: 305

Text #18

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1637. Min Act: -0.1700

Data Index: 7428834 (Open Web Text)

Max Activating Token Index: 374

Text #19

Max Range: 3.3291. Min Range: -3.3291

Max Act: 3.1419. Min Act: -0.1700

Data Index: 3107700 (Open Web Text)

Max Activating Token Index: 45