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

Dataset: Open Web Text

Neuron 556 in Layer 5

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: 3.2720. Min Range: -3.2720

Max Act: 3.2720. Min Act: -0.1700

Data Index: 34052 (Open Web Text)

Max Activating Token Index: 850

Text #1

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.2520. Min Act: -0.1700

Data Index: 6254368 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.2286. Min Act: -0.1700

Data Index: 3800595 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.1845. Min Act: -0.1700

Data Index: 968229 (Open Web Text)

Max Activating Token Index: 302

Text #4

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.2049. Min Act: -0.1700

Data Index: 7279662 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0997. Min Act: -0.1700

Data Index: 270892 (Open Web Text)

Max Activating Token Index: 521

Text #6

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.1230. Min Act: -0.1700

Data Index: 7116699 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0992. Min Act: -0.1700

Data Index: 5573231 (Open Web Text)

Max Activating Token Index: 886

Text #8

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0803. Min Act: -0.1700

Data Index: 2821295 (Open Web Text)

Max Activating Token Index: 1014

Text #9

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0556. Min Act: -0.1700

Data Index: 5832156 (Open Web Text)

Max Activating Token Index: 703

Text #10

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0408. Min Act: -0.1700

Data Index: 6300170 (Open Web Text)

Max Activating Token Index: 799

Text #11

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0201. Min Act: -0.1700

Data Index: 6767856 (Open Web Text)

Max Activating Token Index: 436

Text #12

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0381. Min Act: -0.1700

Data Index: 7162129 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0443. Min Act: -0.1700

Data Index: 2644827 (Open Web Text)

Max Activating Token Index: 537

Text #14

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0162. Min Act: -0.1700

Data Index: 5179560 (Open Web Text)

Max Activating Token Index: 886

Text #15

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0360. Min Act: -0.1700

Data Index: 4573101 (Open Web Text)

Max Activating Token Index: 585

Text #16

Max Range: 3.2720. Min Range: -3.2720

Max Act: 2.9923. Min Act: -0.1700

Data Index: 5736019 (Open Web Text)

Max Activating Token Index: 864

Text #17

Max Range: 3.2720. Min Range: -3.2720

Max Act: 3.0016. Min Act: -0.1700

Data Index: 3161625 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 3.2720. Min Range: -3.2720

Max Act: 2.9911. Min Act: -0.1700

Data Index: 8467712 (Open Web Text)

Max Activating Token Index: 746

Text #19

Max Range: 3.2720. Min Range: -3.2720

Max Act: 2.9852. Min Act: -0.1700

Data Index: 6444842 (Open Web Text)

Max Activating Token Index: 402