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

Dataset: Open Web Text

Neuron 248 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: 3.0389. Min Range: -3.0389

Max Act: 3.0389. Min Act: -0.1700

Data Index: 485412 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 3.0389. Min Range: -3.0389

Max Act: 3.0109. Min Act: -0.1700

Data Index: 847688 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.9657. Min Act: -0.1700

Data Index: 485411 (Open Web Text)

Max Activating Token Index: 381

Text #3

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.9456. Min Act: -0.1700

Data Index: 6094158 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8865. Min Act: -0.1700

Data Index: 3262037 (Open Web Text)

Max Activating Token Index: 580

Text #5

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8974. Min Act: -0.1700

Data Index: 3754033 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8419. Min Act: -0.1700

Data Index: 2966926 (Open Web Text)

Max Activating Token Index: 599

Text #7

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8606. Min Act: -0.1700

Data Index: 5699028 (Open Web Text)

Max Activating Token Index: 329

Text #8

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8768. Min Act: -0.1700

Data Index: 1904807 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8723. Min Act: -0.1700

Data Index: 714148 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8392. Min Act: -0.1700

Data Index: 2276797 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8301. Min Act: -0.1700

Data Index: 7616334 (Open Web Text)

Max Activating Token Index: 751

Text #12

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8515. Min Act: -0.1700

Data Index: 8004611 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8235. Min Act: -0.1700

Data Index: 207574 (Open Web Text)

Max Activating Token Index: 727

Text #14

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8237. Min Act: -0.1700

Data Index: 3262035 (Open Web Text)

Max Activating Token Index: 880

Text #15

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7917. Min Act: -0.1700

Data Index: 6027906 (Open Web Text)

Max Activating Token Index: 307

Text #16

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8074. Min Act: -0.1700

Data Index: 4999122 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.8106. Min Act: -0.1700

Data Index: 1505289 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7822. Min Act: -0.1700

Data Index: 271316 (Open Web Text)

Max Activating Token Index: 102

Text #19

Max Range: 3.0389. Min Range: -3.0389

Max Act: 2.7727. Min Act: -0.1700

Data Index: 3262036 (Open Web Text)

Max Activating Token Index: 309