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

Dataset: Open Web Text

Neuron 1561 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: 3.7959. Min Range: -3.7959

Max Act: 3.7959. Min Act: -0.1700

Data Index: 6397232 (Open Web Text)

Max Activating Token Index: 761

Text #1

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.7592. Min Act: -0.1700

Data Index: 923303 (Open Web Text)

Max Activating Token Index: 936

Text #2

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.7169. Min Act: -0.1700

Data Index: 8139629 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6728. Min Act: -0.1700

Data Index: 1320887 (Open Web Text)

Max Activating Token Index: 874

Text #4

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6852. Min Act: -0.1700

Data Index: 5068074 (Open Web Text)

Max Activating Token Index: 526

Text #5

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6652. Min Act: -0.1700

Data Index: 7416011 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6556. Min Act: -0.1700

Data Index: 3417836 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6279. Min Act: -0.1700

Data Index: 738673 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6313. Min Act: -0.1700

Data Index: 5262578 (Open Web Text)

Max Activating Token Index: 354

Text #9

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6424. Min Act: -0.1700

Data Index: 8710107 (Open Web Text)

Max Activating Token Index: 387

Text #10

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6367. Min Act: -0.1700

Data Index: 3144117 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6284. Min Act: -0.1700

Data Index: 340040 (Open Web Text)

Max Activating Token Index: 685

Text #12

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6314. Min Act: -0.1700

Data Index: 4457883 (Open Web Text)

Max Activating Token Index: 120

Text #13

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6090. Min Act: -0.1700

Data Index: 4327212 (Open Web Text)

Max Activating Token Index: 928

Text #14

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6126. Min Act: -0.1700

Data Index: 995288 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6091. Min Act: -0.1700

Data Index: 8521947 (Open Web Text)

Max Activating Token Index: 63

Text #16

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6285. Min Act: -0.1700

Data Index: 7763818 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1202339 (Open Web Text)

Max Activating Token Index: 930

Text #18

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6178. Min Act: -0.1700

Data Index: 6128679 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 3.7959. Min Range: -3.7959

Max Act: 3.6163. Min Act: -0.1700

Data Index: 3830053 (Open Web Text)

Max Activating Token Index: 164