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

Dataset: Open Web Text

Neuron 906 in Layer 0

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: 1.6987. Min Range: -1.6987

Max Act: 1.6973. Min Act: -0.1700

Data Index: 409416 (Open Web Text)

Max Activating Token Index: 232

Text #1

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6987. Min Act: -0.1631

Data Index: 4189734 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6953. Min Act: -0.1699

Data Index: 1797147 (Open Web Text)

Max Activating Token Index: 514

Text #3

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6611. Min Act: -0.1700

Data Index: 8722970 (Open Web Text)

Max Activating Token Index: 824

Text #4

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6518. Min Act: -0.1700

Data Index: 2234296 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6389. Min Act: -0.1700

Data Index: 6737611 (Open Web Text)

Max Activating Token Index: 324

Text #6

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6460. Min Act: -0.1700

Data Index: 1094635 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6261. Min Act: -0.1678

Data Index: 8592232 (Open Web Text)

Max Activating Token Index: 917

Text #8

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6125. Min Act: -0.1700

Data Index: 5037608 (Open Web Text)

Max Activating Token Index: 454

Text #9

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6115. Min Act: -0.1700

Data Index: 5037623 (Open Web Text)

Max Activating Token Index: 169

Text #10

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6009. Min Act: -0.1700

Data Index: 6497329 (Open Web Text)

Max Activating Token Index: 597

Text #11

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5839. Min Act: -0.1700

Data Index: 496651 (Open Web Text)

Max Activating Token Index: 525

Text #12

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5832. Min Act: -0.1700

Data Index: 7415797 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5815. Min Act: -0.1700

Data Index: 315015 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5849. Min Act: -0.1700

Data Index: 1186446 (Open Web Text)

Max Activating Token Index: 188

Text #15

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5843. Min Act: -0.1700

Data Index: 2181294 (Open Web Text)

Max Activating Token Index: 590

Text #16

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5843. Min Act: -0.1700

Data Index: 6633525 (Open Web Text)

Max Activating Token Index: 93

Text #17

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5732. Min Act: -0.1700

Data Index: 3837876 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5761. Min Act: -0.1693

Data Index: 6254749 (Open Web Text)

Max Activating Token Index: 493

Text #19

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5701. Min Act: -0.1700

Data Index: 3296723 (Open Web Text)

Max Activating Token Index: 637