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

Dataset: Open Web Text

Neuron 648 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: 0.6023. Min Range: -0.6023

Max Act: 0.6023. Min Act: -0.1700

Data Index: 2460559 (Open Web Text)

Max Activating Token Index: 759

Text #1

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.5754. Min Act: -0.1700

Data Index: 720762 (Open Web Text)

Max Activating Token Index: 707

Text #2

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.5581. Min Act: -0.1700

Data Index: 7463922 (Open Web Text)

Max Activating Token Index: 705

Text #3

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.5362. Min Act: -0.1700

Data Index: 5341545 (Open Web Text)

Max Activating Token Index: 182

Text #4

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.5372. Min Act: -0.1700

Data Index: 1176938 (Open Web Text)

Max Activating Token Index: 185

Text #5

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4932. Min Act: -0.1700

Data Index: 1274272 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4778. Min Act: -0.1700

Data Index: 2130154 (Open Web Text)

Max Activating Token Index: 706

Text #7

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4660. Min Act: -0.1700

Data Index: 5877668 (Open Web Text)

Max Activating Token Index: 705

Text #8

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4599. Min Act: -0.1700

Data Index: 84150 (Open Web Text)

Max Activating Token Index: 168

Text #9

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4657. Min Act: -0.1700

Data Index: 8053986 (Open Web Text)

Max Activating Token Index: 210

Text #10

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4668. Min Act: -0.1700

Data Index: 4068843 (Open Web Text)

Max Activating Token Index: 163

Text #11

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4468. Min Act: -0.1700

Data Index: 3607376 (Open Web Text)

Max Activating Token Index: 793

Text #12

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4416. Min Act: -0.1700

Data Index: 7245507 (Open Web Text)

Max Activating Token Index: 708

Text #13

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4350. Min Act: -0.1700

Data Index: 7475570 (Open Web Text)

Max Activating Token Index: 765

Text #14

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4439. Min Act: -0.1700

Data Index: 1533275 (Open Web Text)

Max Activating Token Index: 165

Text #15

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4594. Min Act: -0.1700

Data Index: 2073887 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4299. Min Act: -0.1700

Data Index: 3260194 (Open Web Text)

Max Activating Token Index: 155

Text #17

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4102. Min Act: -0.1700

Data Index: 190635 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4356. Min Act: -0.1700

Data Index: 6864961 (Open Web Text)

Max Activating Token Index: 698

Text #19

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4175. Min Act: -0.1700

Data Index: 3630719 (Open Web Text)

Max Activating Token Index: 675