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

Dataset: Open Web Text

Neuron 147 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: 1.2002. Min Range: -1.2002

Max Act: 1.2002. Min Act: -0.1700

Data Index: 3046458 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1884. Min Act: -0.1700

Data Index: 2583341 (Open Web Text)

Max Activating Token Index: 522

Text #2

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1830. Min Act: -0.1700

Data Index: 2493960 (Open Web Text)

Max Activating Token Index: 339

Text #3

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1767. Min Act: -0.1700

Data Index: 4416688 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1807. Min Act: -0.1700

Data Index: 8654338 (Open Web Text)

Max Activating Token Index: 1009

Text #5

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1747. Min Act: -0.1697

Data Index: 3284730 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1761. Min Act: -0.1700

Data Index: 4950462 (Open Web Text)

Max Activating Token Index: 668

Text #7

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1745. Min Act: -0.1700

Data Index: 900464 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1625. Min Act: -0.1700

Data Index: 1241888 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1698. Min Act: -0.1700

Data Index: 852493 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1537. Min Act: -0.1700

Data Index: 6539054 (Open Web Text)

Max Activating Token Index: 504

Text #11

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1522. Min Act: -0.1700

Data Index: 5649706 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1515. Min Act: -0.1696

Data Index: 5353361 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1542. Min Act: -0.1700

Data Index: 1791422 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1596. Min Act: -0.1699

Data Index: 2401417 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1574. Min Act: -0.1700

Data Index: 332007 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1598. Min Act: -0.1698

Data Index: 1542329 (Open Web Text)

Max Activating Token Index: 686

Text #17

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1642. Min Act: -0.1697

Data Index: 3027975 (Open Web Text)

Max Activating Token Index: 955

Text #18

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1547. Min Act: -0.1700

Data Index: 3003950 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1597. Min Act: -0.1700

Data Index: 2354106 (Open Web Text)

Max Activating Token Index: 795