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

Dataset: Open Web Text

Neuron 1064 in Layer 3

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: 3.4039. Min Range: -3.4039

Max Act: 3.4039. Min Act: -0.1700

Data Index: 3998931 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.3484. Min Act: -0.1700

Data Index: 5358062 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2928. Min Act: -0.1700

Data Index: 5780978 (Open Web Text)

Max Activating Token Index: 635

Text #3

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2788. Min Act: -0.1700

Data Index: 4407923 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2445. Min Act: -0.1700

Data Index: 2947192 (Open Web Text)

Max Activating Token Index: 290

Text #5

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2400. Min Act: -0.1700

Data Index: 5276251 (Open Web Text)

Max Activating Token Index: 335

Text #6

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2414. Min Act: -0.1700

Data Index: 2323920 (Open Web Text)

Max Activating Token Index: 48

Text #7

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2414. Min Act: -0.1700

Data Index: 1357780 (Open Web Text)

Max Activating Token Index: 298

Text #8

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2221. Min Act: -0.1700

Data Index: 5821938 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2264. Min Act: -0.1700

Data Index: 6623704 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2129. Min Act: -0.1700

Data Index: 6329132 (Open Web Text)

Max Activating Token Index: 558

Text #11

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2297. Min Act: -0.1700

Data Index: 4516717 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2408. Min Act: -0.1700

Data Index: 1090107 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.1965. Min Act: -0.1700

Data Index: 3832225 (Open Web Text)

Max Activating Token Index: 391

Text #14

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2033. Min Act: -0.1700

Data Index: 3288954 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.1625. Min Act: -0.1700

Data Index: 5213677 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.1525. Min Act: -0.1700

Data Index: 1305210 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.1687. Min Act: -0.1700

Data Index: 3163008 (Open Web Text)

Max Activating Token Index: 724

Text #18

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2010. Min Act: -0.1700

Data Index: 5705218 (Open Web Text)

Max Activating Token Index: 657

Text #19

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.1590. Min Act: -0.1700

Data Index: 5882612 (Open Web Text)

Max Activating Token Index: 443