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

Dataset: Open Web Text

Neuron 969 in Layer 2

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: 2.3577. Min Range: -2.3577

Max Act: 2.3577. Min Act: -0.1700

Data Index: 3224362 (Open Web Text)

Max Activating Token Index: 159

Text #1

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.3284. Min Act: -0.1700

Data Index: 3449893 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2314. Min Act: -0.1700

Data Index: 2493726 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2244. Min Act: -0.1700

Data Index: 7945966 (Open Web Text)

Max Activating Token Index: 658

Text #4

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2173. Min Act: -0.1700

Data Index: 269517 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2157. Min Act: -0.1700

Data Index: 1437841 (Open Web Text)

Max Activating Token Index: 396

Text #6

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2082. Min Act: -0.1700

Data Index: 3310379 (Open Web Text)

Max Activating Token Index: 208

Text #7

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1989. Min Act: -0.1700

Data Index: 3068409 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1879. Min Act: -0.1700

Data Index: 3288281 (Open Web Text)

Max Activating Token Index: 571

Text #9

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2067. Min Act: -0.1700

Data Index: 5541109 (Open Web Text)

Max Activating Token Index: 392

Text #10

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2009. Min Act: -0.1700

Data Index: 3252330 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2011. Min Act: -0.1700

Data Index: 5066645 (Open Web Text)

Max Activating Token Index: 730

Text #12

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2031. Min Act: -0.1700

Data Index: 289482 (Open Web Text)

Max Activating Token Index: 312

Text #13

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1932. Min Act: -0.1700

Data Index: 7354046 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1712. Min Act: -0.1700

Data Index: 6370716 (Open Web Text)

Max Activating Token Index: 666

Text #15

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1787. Min Act: -0.1700

Data Index: 5246969 (Open Web Text)

Max Activating Token Index: 655

Text #16

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1827. Min Act: -0.1700

Data Index: 6138242 (Open Web Text)

Max Activating Token Index: 323

Text #17

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1762. Min Act: -0.1700

Data Index: 707268 (Open Web Text)

Max Activating Token Index: 461

Text #18

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1882. Min Act: -0.1700

Data Index: 6074463 (Open Web Text)

Max Activating Token Index: 622

Text #19

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1710. Min Act: -0.1700

Data Index: 5546670 (Open Web Text)

Max Activating Token Index: 433