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

Dataset: Open Web Text

Neuron 2877 in Layer 3

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: 2.0601. Min Range: -2.0601

Max Act: 2.0601. Min Act: -0.1695

Data Index: 6785098 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0356. Min Act: -0.1697

Data Index: 2863050 (Open Web Text)

Max Activating Token Index: 750

Text #2

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0501. Min Act: -0.1670

Data Index: 423745 (Open Web Text)

Max Activating Token Index: 910

Text #3

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0130. Min Act: -0.1637

Data Index: 5781367 (Open Web Text)

Max Activating Token Index: 935

Text #4

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0230. Min Act: -0.1642

Data Index: 8214967 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0237. Min Act: -0.1695

Data Index: 26503 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0572. Min Act: -0.1697

Data Index: 8172202 (Open Web Text)

Max Activating Token Index: 710

Text #7

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0057. Min Act: -0.1692

Data Index: 4532964 (Open Web Text)

Max Activating Token Index: 747

Text #8

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0340. Min Act: -0.1700

Data Index: 639390 (Open Web Text)

Max Activating Token Index: 254

Text #9

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0244. Min Act: -0.1699

Data Index: 4527511 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0097. Min Act: -0.1623

Data Index: 7104413 (Open Web Text)

Max Activating Token Index: 277

Text #11

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9691. Min Act: -0.1699

Data Index: 627491 (Open Web Text)

Max Activating Token Index: 843

Text #12

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9782. Min Act: -0.1694

Data Index: 6442318 (Open Web Text)

Max Activating Token Index: 400

Text #13

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9675. Min Act: -0.1695

Data Index: 2870855 (Open Web Text)

Max Activating Token Index: 889

Text #14

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9955. Min Act: -0.1700

Data Index: 1042471 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9887. Min Act: -0.1697

Data Index: 3557206 (Open Web Text)

Max Activating Token Index: 725

Text #16

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9720. Min Act: -0.1542

Data Index: 3117360 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9937. Min Act: -0.1687

Data Index: 2950414 (Open Web Text)

Max Activating Token Index: 435

Text #18

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0108. Min Act: -0.1684

Data Index: 8082192 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9867. Min Act: -0.1671

Data Index: 203914 (Open Web Text)

Max Activating Token Index: 318