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

Dataset: Open Web Text

Neuron 3028 in Layer 4

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: 3.9966. Min Range: -3.9966

Max Act: 3.9966. Min Act: -0.1700

Data Index: 6960657 (Open Web Text)

Max Activating Token Index: 481

Text #1

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.9290. Min Act: -0.1700

Data Index: 1797214 (Open Web Text)

Max Activating Token Index: 731

Text #2

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.9084. Min Act: -0.1700

Data Index: 815320 (Open Web Text)

Max Activating Token Index: 247

Text #3

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.9264. Min Act: -0.1700

Data Index: 3738231 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8798. Min Act: -0.1700

Data Index: 2390545 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.9102. Min Act: -0.1700

Data Index: 2269983 (Open Web Text)

Max Activating Token Index: 662

Text #6

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8526. Min Act: -0.1700

Data Index: 3841783 (Open Web Text)

Max Activating Token Index: 122

Text #7

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8311. Min Act: -0.1700

Data Index: 4024536 (Open Web Text)

Max Activating Token Index: 886

Text #8

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7925. Min Act: -0.1700

Data Index: 925495 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8194. Min Act: -0.1700

Data Index: 5417266 (Open Web Text)

Max Activating Token Index: 876

Text #10

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8259. Min Act: -0.1700

Data Index: 498361 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8027. Min Act: -0.1700

Data Index: 7268497 (Open Web Text)

Max Activating Token Index: 919

Text #12

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7760. Min Act: -0.1700

Data Index: 8443062 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7740. Min Act: -0.1700

Data Index: 1567386 (Open Web Text)

Max Activating Token Index: 331

Text #14

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7853. Min Act: -0.1700

Data Index: 177157 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7899. Min Act: -0.1700

Data Index: 4160288 (Open Web Text)

Max Activating Token Index: 627

Text #16

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7511. Min Act: -0.1700

Data Index: 2831125 (Open Web Text)

Max Activating Token Index: 528

Text #17

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7718. Min Act: -0.1700

Data Index: 1061477 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7758. Min Act: -0.1700

Data Index: 1159996 (Open Web Text)

Max Activating Token Index: 257

Text #19

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7297. Min Act: -0.1700

Data Index: 4489931 (Open Web Text)

Max Activating Token Index: 683