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

Dataset: Open Web Text

Neuron 1416 in Layer 2

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: 1.0916. Min Range: -1.0916

Max Act: 1.0916. Min Act: -0.1700

Data Index: 8571862 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0677. Min Act: -0.1700

Data Index: 2220064 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0264. Min Act: -0.1698

Data Index: 8798504 (Open Web Text)

Max Activating Token Index: 344

Text #3

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0180. Min Act: -0.1700

Data Index: 4488161 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0110. Min Act: -0.1700

Data Index: 7278443 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0166. Min Act: -0.1699

Data Index: 8192816 (Open Web Text)

Max Activating Token Index: 333

Text #6

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0000. Min Act: -0.1666

Data Index: 1061635 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9928. Min Act: -0.1695

Data Index: 5576608 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9896. Min Act: -0.1562

Data Index: 4942057 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9855. Min Act: -0.1678

Data Index: 5342000 (Open Web Text)

Max Activating Token Index: 53

Text #10

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9860. Min Act: -0.1699

Data Index: 7504201 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0007. Min Act: -0.1692

Data Index: 4907682 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9681. Min Act: -0.1700

Data Index: 4035181 (Open Web Text)

Max Activating Token Index: 35

Text #13

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9681. Min Act: -0.1686

Data Index: 2154165 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9899. Min Act: -0.1686

Data Index: 1543793 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9603. Min Act: -0.1684

Data Index: 6874468 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9605. Min Act: -0.1698

Data Index: 1218497 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9639. Min Act: -0.1642

Data Index: 5796028 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9601. Min Act: -0.1686

Data Index: 2720586 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9654. Min Act: -0.1699

Data Index: 6433957 (Open Web Text)

Max Activating Token Index: 238