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

Dataset: Open Web Text

Neuron 1569 in Layer 1

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: 1.9892. Min Range: -1.9892

Max Act: 1.9892. Min Act: -0.1700

Data Index: 4693325 (Open Web Text)

Max Activating Token Index: 258

Text #1

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.9838. Min Act: -0.1700

Data Index: 4693324 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.9814. Min Act: -0.1700

Data Index: 4693326 (Open Web Text)

Max Activating Token Index: 791

Text #3

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.9696. Min Act: -0.1700

Data Index: 4693322 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.9507. Min Act: -0.1700

Data Index: 4693320 (Open Web Text)

Max Activating Token Index: 319

Text #5

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.9370. Min Act: -0.1700

Data Index: 4693323 (Open Web Text)

Max Activating Token Index: 823

Text #6

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8840. Min Act: -0.1700

Data Index: 4693317 (Open Web Text)

Max Activating Token Index: 348

Text #7

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8966. Min Act: -0.1700

Data Index: 4693313 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8852. Min Act: -0.1700

Data Index: 4693327 (Open Web Text)

Max Activating Token Index: 299

Text #9

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8708. Min Act: -0.1700

Data Index: 4693316 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8842. Min Act: -0.1700

Data Index: 4693321 (Open Web Text)

Max Activating Token Index: 752

Text #11

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8786. Min Act: -0.1700

Data Index: 4693314 (Open Web Text)

Max Activating Token Index: 370

Text #12

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8768. Min Act: -0.1700

Data Index: 2373667 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8862. Min Act: -0.1700

Data Index: 7344316 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8771. Min Act: -0.1700

Data Index: 4693319 (Open Web Text)

Max Activating Token Index: 206

Text #15

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8717. Min Act: -0.1700

Data Index: 4693312 (Open Web Text)

Max Activating Token Index: 881

Text #16

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8628. Min Act: -0.1700

Data Index: 6081587 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8660. Min Act: -0.1700

Data Index: 2832311 (Open Web Text)

Max Activating Token Index: 171

Text #18

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8571. Min Act: -0.1700

Data Index: 3806274 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.8360. Min Act: -0.1700

Data Index: 4693311 (Open Web Text)

Max Activating Token Index: 695