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

Dataset: Open Web Text

Neuron 951 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: 1.2837. Min Range: -1.2837

Max Act: 1.2797. Min Act: -0.1616

Data Index: 5604531 (Open Web Text)

Max Activating Token Index: 90

Text #1

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2837. Min Act: -0.1240

Data Index: 4811855 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2587. Min Act: -0.1600

Data Index: 884594 (Open Web Text)

Max Activating Token Index: 396

Text #3

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2635. Min Act: -0.1688

Data Index: 913623 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2550. Min Act: -0.1590

Data Index: 1978445 (Open Web Text)

Max Activating Token Index: 874

Text #5

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2631. Min Act: -0.1583

Data Index: 6504127 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2477. Min Act: -0.1625

Data Index: 4262221 (Open Web Text)

Max Activating Token Index: 325

Text #7

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2431. Min Act: -0.1699

Data Index: 5131658 (Open Web Text)

Max Activating Token Index: 88

Text #8

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2430. Min Act: -0.1636

Data Index: 2355191 (Open Web Text)

Max Activating Token Index: 151

Text #9

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2413. Min Act: -0.1650

Data Index: 5551746 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2349. Min Act: -0.1578

Data Index: 4811850 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2332. Min Act: -0.1518

Data Index: 7784175 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2258. Min Act: -0.1687

Data Index: 5137108 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2286. Min Act: -0.1627

Data Index: 5269594 (Open Web Text)

Max Activating Token Index: 325

Text #14

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2298. Min Act: -0.1596

Data Index: 1610051 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2238. Min Act: -0.1671

Data Index: 7374436 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2160. Min Act: -0.1492

Data Index: 209861 (Open Web Text)

Max Activating Token Index: 213

Text #17

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2195. Min Act: -0.1557

Data Index: 3592627 (Open Web Text)

Max Activating Token Index: 471

Text #18

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2117. Min Act: -0.1609

Data Index: 520052 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2122. Min Act: -0.1611

Data Index: 4173118 (Open Web Text)

Max Activating Token Index: 386