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

Dataset: Open Web Text

Neuron 951 in Layer 6

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: 4.2796. Min Range: -4.2796

Max Act: 4.2796. Min Act: -0.1700

Data Index: 2396267 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 4.2796. Min Range: -4.2796

Max Act: 4.1491. Min Act: -0.1700

Data Index: 4638376 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 4.2796. Min Range: -4.2796

Max Act: 4.0213. Min Act: -0.1700

Data Index: 1558479 (Open Web Text)

Max Activating Token Index: 446

Text #3

Max Range: 4.2796. Min Range: -4.2796

Max Act: 4.0426. Min Act: -0.1700

Data Index: 4284261 (Open Web Text)

Max Activating Token Index: 134

Text #4

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.9811. Min Act: -0.1700

Data Index: 2519387 (Open Web Text)

Max Activating Token Index: 775

Text #5

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.9182. Min Act: -0.1700

Data Index: 2934677 (Open Web Text)

Max Activating Token Index: 1000

Text #6

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.9210. Min Act: -0.1700

Data Index: 4175437 (Open Web Text)

Max Activating Token Index: 863

Text #7

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.9077. Min Act: -0.1700

Data Index: 8343611 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8826. Min Act: -0.1700

Data Index: 5102793 (Open Web Text)

Max Activating Token Index: 128

Text #9

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8891. Min Act: -0.1700

Data Index: 5607742 (Open Web Text)

Max Activating Token Index: 399

Text #10

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.7896. Min Act: -0.1700

Data Index: 5411764 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8312. Min Act: -0.1700

Data Index: 2498168 (Open Web Text)

Max Activating Token Index: 464

Text #12

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8564. Min Act: -0.1700

Data Index: 622337 (Open Web Text)

Max Activating Token Index: 353

Text #13

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8465. Min Act: -0.1700

Data Index: 7657088 (Open Web Text)

Max Activating Token Index: 900

Text #14

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8113. Min Act: -0.1700

Data Index: 7604442 (Open Web Text)

Max Activating Token Index: 338

Text #15

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8281. Min Act: -0.1700

Data Index: 4998645 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8563. Min Act: -0.1700

Data Index: 6948194 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8456. Min Act: -0.1700

Data Index: 6122960 (Open Web Text)

Max Activating Token Index: 972

Text #18

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8431. Min Act: -0.1700

Data Index: 6483030 (Open Web Text)

Max Activating Token Index: 261

Text #19

Max Range: 4.2796. Min Range: -4.2796

Max Act: 3.8227. Min Act: -0.1700

Data Index: 5183846 (Open Web Text)

Max Activating Token Index: 534