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

Dataset: Open Web Text

Neuron 810 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: 4.1047. Min Range: -4.1047

Max Act: 4.1047. Min Act: -0.1700

Data Index: 675433 (Open Web Text)

Max Activating Token Index: 451

Text #1

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9875. Min Act: -0.1700

Data Index: 2955278 (Open Web Text)

Max Activating Token Index: 693

Text #2

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9521. Min Act: -0.1700

Data Index: 1449730 (Open Web Text)

Max Activating Token Index: 562

Text #3

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9419. Min Act: -0.1700

Data Index: 7879833 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9645. Min Act: -0.1700

Data Index: 5669602 (Open Web Text)

Max Activating Token Index: 216

Text #5

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9447. Min Act: -0.1700

Data Index: 693698 (Open Web Text)

Max Activating Token Index: 482

Text #6

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9622. Min Act: -0.1700

Data Index: 136896 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9260. Min Act: -0.1700

Data Index: 1521044 (Open Web Text)

Max Activating Token Index: 696

Text #8

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9254. Min Act: -0.1700

Data Index: 3656250 (Open Web Text)

Max Activating Token Index: 806

Text #9

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9133. Min Act: -0.1700

Data Index: 4282234 (Open Web Text)

Max Activating Token Index: 311

Text #10

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9368. Min Act: -0.1700

Data Index: 2158381 (Open Web Text)

Max Activating Token Index: 321

Text #11

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9242. Min Act: -0.1700

Data Index: 3891046 (Open Web Text)

Max Activating Token Index: 732

Text #12

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9381. Min Act: -0.1700

Data Index: 3970682 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.8829. Min Act: -0.1700

Data Index: 4935741 (Open Web Text)

Max Activating Token Index: 673

Text #14

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.8606. Min Act: -0.1700

Data Index: 2663257 (Open Web Text)

Max Activating Token Index: 494

Text #15

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9025. Min Act: -0.1700

Data Index: 3460987 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.8783. Min Act: -0.1700

Data Index: 874000 (Open Web Text)

Max Activating Token Index: 795

Text #17

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.9104. Min Act: -0.1700

Data Index: 3890115 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.8600. Min Act: -0.1700

Data Index: 4552497 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.8552. Min Act: -0.1700

Data Index: 8676750 (Open Web Text)

Max Activating Token Index: 908