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

Dataset: Open Web Text

Neuron 2451 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: 3.5860. Min Range: -3.5860

Max Act: 3.5860. Min Act: -0.1700

Data Index: 1392031 (Open Web Text)

Max Activating Token Index: 352

Text #1

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5644. Min Act: -0.1700

Data Index: 3587188 (Open Web Text)

Max Activating Token Index: 81

Text #2

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5817. Min Act: -0.1700

Data Index: 8146395 (Open Web Text)

Max Activating Token Index: 230

Text #3

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5666. Min Act: -0.1700

Data Index: 190388 (Open Web Text)

Max Activating Token Index: 132

Text #4

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5347. Min Act: -0.1699

Data Index: 981575 (Open Web Text)

Max Activating Token Index: 653

Text #5

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5293. Min Act: -0.1700

Data Index: 3553883 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5306. Min Act: -0.1700

Data Index: 717376 (Open Web Text)

Max Activating Token Index: 864

Text #7

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5214. Min Act: -0.1700

Data Index: 8657759 (Open Web Text)

Max Activating Token Index: 688

Text #8

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5087. Min Act: -0.1700

Data Index: 8502680 (Open Web Text)

Max Activating Token Index: 106

Text #9

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5094. Min Act: -0.1700

Data Index: 5785472 (Open Web Text)

Max Activating Token Index: 232

Text #10

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.4576. Min Act: -0.1700

Data Index: 2433891 (Open Web Text)

Max Activating Token Index: 776

Text #11

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5072. Min Act: -0.1700

Data Index: 8740311 (Open Web Text)

Max Activating Token Index: 103

Text #12

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5201. Min Act: -0.1700

Data Index: 6626414 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5014. Min Act: -0.1700

Data Index: 2230880 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.4711. Min Act: -0.1700

Data Index: 1398990 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.4725. Min Act: -0.1700

Data Index: 5708751 (Open Web Text)

Max Activating Token Index: 639

Text #16

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5007. Min Act: -0.1700

Data Index: 5620394 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.4887. Min Act: -0.1700

Data Index: 4600985 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.4916. Min Act: -0.1700

Data Index: 175612 (Open Web Text)

Max Activating Token Index: 332

Text #19

Max Range: 3.5860. Min Range: -3.5860

Max Act: 3.5047. Min Act: -0.1700

Data Index: 2900592 (Open Web Text)

Max Activating Token Index: 518