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

Dataset: Open Web Text

Neuron 1760 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: 1.8585. Min Range: -1.8585

Max Act: 1.8585. Min Act: -0.1700

Data Index: 6787197 (Open Web Text)

Max Activating Token Index: 532

Text #1

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7674. Min Act: -0.1700

Data Index: 86512 (Open Web Text)

Max Activating Token Index: 254

Text #2

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7628. Min Act: -0.1700

Data Index: 4392332 (Open Web Text)

Max Activating Token Index: 273

Text #3

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7549. Min Act: -0.1700

Data Index: 2350445 (Open Web Text)

Max Activating Token Index: 202

Text #4

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7316. Min Act: -0.1695

Data Index: 8787843 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7265. Min Act: -0.1700

Data Index: 8568856 (Open Web Text)

Max Activating Token Index: 383

Text #6

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7248. Min Act: -0.1700

Data Index: 8362480 (Open Web Text)

Max Activating Token Index: 807

Text #7

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7219. Min Act: -0.1700

Data Index: 4679109 (Open Web Text)

Max Activating Token Index: 129

Text #8

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7109. Min Act: -0.1700

Data Index: 1811378 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7140. Min Act: -0.1700

Data Index: 8359969 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7040. Min Act: -0.1700

Data Index: 8524497 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6992. Min Act: -0.1700

Data Index: 7165675 (Open Web Text)

Max Activating Token Index: 331

Text #12

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6978. Min Act: -0.1699

Data Index: 5106901 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7005. Min Act: -0.1700

Data Index: 8069840 (Open Web Text)

Max Activating Token Index: 74

Text #14

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6844. Min Act: -0.1700

Data Index: 4634235 (Open Web Text)

Max Activating Token Index: 80

Text #15

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6818. Min Act: -0.1700

Data Index: 6078938 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6810. Min Act: -0.1700

Data Index: 1969666 (Open Web Text)

Max Activating Token Index: 536

Text #17

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6913. Min Act: -0.1700

Data Index: 3338116 (Open Web Text)

Max Activating Token Index: 312

Text #18

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6905. Min Act: -0.1700

Data Index: 8553632 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6782. Min Act: -0.1700

Data Index: 8097723 (Open Web Text)

Max Activating Token Index: 36