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

Dataset: Open Web Text

Neuron 1966 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: 4.2721. Min Range: -4.2721

Max Act: 4.2721. Min Act: -0.1680

Data Index: 3945115 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.2193. Min Act: -0.1685

Data Index: 1686874 (Open Web Text)

Max Activating Token Index: 675

Text #2

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.2236. Min Act: -0.1696

Data Index: 4362689 (Open Web Text)

Max Activating Token Index: 554

Text #3

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.1601. Min Act: -0.1683

Data Index: 8633362 (Open Web Text)

Max Activating Token Index: 533

Text #4

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.1556. Min Act: -0.1520

Data Index: 1077330 (Open Web Text)

Max Activating Token Index: 458

Text #5

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.1776. Min Act: -0.1474

Data Index: 7931796 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.1700. Min Act: -0.1700

Data Index: 5233729 (Open Web Text)

Max Activating Token Index: 692

Text #7

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.1794. Min Act: -0.1699

Data Index: 5716682 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.1327. Min Act: -0.1700

Data Index: 8417154 (Open Web Text)

Max Activating Token Index: 524

Text #9

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.1016. Min Act: -0.1413

Data Index: 3762191 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.1055. Min Act: -0.1639

Data Index: 737340 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0674. Min Act: -0.1563

Data Index: 821078 (Open Web Text)

Max Activating Token Index: 616

Text #12

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0441. Min Act: -0.1697

Data Index: 7130109 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0043. Min Act: -0.1699

Data Index: 3496535 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0160. Min Act: -0.1700

Data Index: 8221780 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0058. Min Act: -0.1650

Data Index: 3419775 (Open Web Text)

Max Activating Token Index: 667

Text #16

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0145. Min Act: -0.1694

Data Index: 1110274 (Open Web Text)

Max Activating Token Index: 704

Text #17

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0168. Min Act: -0.1697

Data Index: 8089071 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0389. Min Act: -0.1697

Data Index: 3125915 (Open Web Text)

Max Activating Token Index: 847

Text #19

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9970. Min Act: -0.1581

Data Index: 2842694 (Open Web Text)

Max Activating Token Index: 709