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

Dataset: Open Web Text

Neuron 1954 in Layer 1

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: 3.2071. Min Range: -3.2071

Max Act: 3.2071. Min Act: -0.1700

Data Index: 7931555 (Open Web Text)

Max Activating Token Index: 246

Text #1

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1676. Min Act: -0.1700

Data Index: 2129538 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1609. Min Act: -0.1700

Data Index: 5832554 (Open Web Text)

Max Activating Token Index: 505

Text #3

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1391. Min Act: -0.1700

Data Index: 6161115 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1453. Min Act: -0.1700

Data Index: 524834 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1345. Min Act: -0.1700

Data Index: 5850684 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1328. Min Act: -0.1700

Data Index: 543901 (Open Web Text)

Max Activating Token Index: 196

Text #7

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1315. Min Act: -0.1700

Data Index: 2840161 (Open Web Text)

Max Activating Token Index: 613

Text #8

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1389. Min Act: -0.1700

Data Index: 3735183 (Open Web Text)

Max Activating Token Index: 506

Text #9

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1335. Min Act: -0.1700

Data Index: 3143843 (Open Web Text)

Max Activating Token Index: 390

Text #10

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1156. Min Act: -0.1700

Data Index: 5581408 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1158. Min Act: -0.1700

Data Index: 1668065 (Open Web Text)

Max Activating Token Index: 913

Text #12

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1141. Min Act: -0.1700

Data Index: 1492085 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1274. Min Act: -0.1700

Data Index: 6137018 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1233. Min Act: -0.1700

Data Index: 6125671 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1217. Min Act: -0.1700

Data Index: 8483881 (Open Web Text)

Max Activating Token Index: 632

Text #16

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1253. Min Act: -0.1700

Data Index: 2446585 (Open Web Text)

Max Activating Token Index: 277

Text #17

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1221. Min Act: -0.1700

Data Index: 7746472 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1199. Min Act: -0.1700

Data Index: 210973 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 3.2071. Min Range: -3.2071

Max Act: 3.1380. Min Act: -0.1700

Data Index: 4041497 (Open Web Text)

Max Activating Token Index: 531