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

Dataset: Open Web Text

Neuron 1801 in Layer 5

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: 3.1736. Min Range: -3.1736

Max Act: 3.1736. Min Act: -0.1700

Data Index: 2297555 (Open Web Text)

Max Activating Token Index: 116

Text #1

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.1421. Min Act: -0.1700

Data Index: 5950994 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.1561. Min Act: -0.1700

Data Index: 2706635 (Open Web Text)

Max Activating Token Index: 703

Text #3

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.1188. Min Act: -0.1700

Data Index: 2553790 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.1329. Min Act: -0.1700

Data Index: 1028329 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0888. Min Act: -0.1700

Data Index: 6395585 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0967. Min Act: -0.1700

Data Index: 3689121 (Open Web Text)

Max Activating Token Index: 940

Text #7

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.1088. Min Act: -0.1700

Data Index: 3507908 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0761. Min Act: -0.1700

Data Index: 1905352 (Open Web Text)

Max Activating Token Index: 759

Text #9

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0850. Min Act: -0.1700

Data Index: 7045800 (Open Web Text)

Max Activating Token Index: 469

Text #10

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0422. Min Act: -0.1700

Data Index: 7892342 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0404. Min Act: -0.1700

Data Index: 3447573 (Open Web Text)

Max Activating Token Index: 342

Text #12

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0241. Min Act: -0.1700

Data Index: 7896732 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0552. Min Act: -0.1700

Data Index: 216460 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0356. Min Act: -0.1700

Data Index: 1049166 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0353. Min Act: -0.1700

Data Index: 6270117 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0122. Min Act: -0.1700

Data Index: 1794264 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0289. Min Act: -0.1700

Data Index: 2537549 (Open Web Text)

Max Activating Token Index: 324

Text #18

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0314. Min Act: -0.1700

Data Index: 1356352 (Open Web Text)

Max Activating Token Index: 284

Text #19

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0272. Min Act: -0.1700

Data Index: 965660 (Open Web Text)

Max Activating Token Index: 920