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

Dataset: Open Web Text

Neuron 25 in Layer 0

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: 3.3285. Min Range: -3.3285

Max Act: 3.3285. Min Act: -0.1700

Data Index: 595717 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1815. Min Act: -0.1700

Data Index: 301262 (Open Web Text)

Max Activating Token Index: 680

Text #2

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1797. Min Act: -0.1700

Data Index: 5792691 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1900. Min Act: -0.1700

Data Index: 527247 (Open Web Text)

Max Activating Token Index: 919

Text #4

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1655. Min Act: -0.1700

Data Index: 4543171 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1499. Min Act: -0.1700

Data Index: 1629411 (Open Web Text)

Max Activating Token Index: 394

Text #6

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1620. Min Act: -0.1700

Data Index: 2608376 (Open Web Text)

Max Activating Token Index: 486

Text #7

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1561. Min Act: -0.1700

Data Index: 6348363 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1436775 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1558. Min Act: -0.1700

Data Index: 5718298 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1591. Min Act: -0.1700

Data Index: 287048 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1432. Min Act: -0.1700

Data Index: 4478699 (Open Web Text)

Max Activating Token Index: 608

Text #12

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1387. Min Act: -0.1700

Data Index: 1259719 (Open Web Text)

Max Activating Token Index: 402

Text #13

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1245. Min Act: -0.1700

Data Index: 27628 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1296. Min Act: -0.1700

Data Index: 3828274 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1260. Min Act: -0.1700

Data Index: 3910195 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1245. Min Act: -0.1700

Data Index: 4012788 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1226. Min Act: -0.1700

Data Index: 5373106 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1201. Min Act: -0.1700

Data Index: 1792509 (Open Web Text)

Max Activating Token Index: 798

Text #19

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1146. Min Act: -0.1700

Data Index: 3901922 (Open Web Text)

Max Activating Token Index: 5