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

Dataset: Open Web Text

Neuron 1859 in Layer 5

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: 2.7701. Min Range: -2.7701

Max Act: 2.7701. Min Act: -0.1700

Data Index: 3465341 (Open Web Text)

Max Activating Token Index: 314

Text #1

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7363. Min Act: -0.1700

Data Index: 5728878 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7442. Min Act: -0.1700

Data Index: 8347045 (Open Web Text)

Max Activating Token Index: 531

Text #3

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7236. Min Act: -0.1700

Data Index: 1432481 (Open Web Text)

Max Activating Token Index: 353

Text #4

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7332. Min Act: -0.1700

Data Index: 7616245 (Open Web Text)

Max Activating Token Index: 514

Text #5

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7105. Min Act: -0.1700

Data Index: 3910133 (Open Web Text)

Max Activating Token Index: 1000

Text #6

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7186. Min Act: -0.1700

Data Index: 51344 (Open Web Text)

Max Activating Token Index: 350

Text #7

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7297. Min Act: -0.1700

Data Index: 5404106 (Open Web Text)

Max Activating Token Index: 305

Text #8

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6909. Min Act: -0.1700

Data Index: 7758810 (Open Web Text)

Max Activating Token Index: 683

Text #9

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6944. Min Act: -0.1700

Data Index: 7720704 (Open Web Text)

Max Activating Token Index: 110

Text #10

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7066. Min Act: -0.1700

Data Index: 4285844 (Open Web Text)

Max Activating Token Index: 655

Text #11

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6918. Min Act: -0.1700

Data Index: 5399246 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6921. Min Act: -0.1700

Data Index: 7250673 (Open Web Text)

Max Activating Token Index: 438

Text #13

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.7012. Min Act: -0.1700

Data Index: 1379457 (Open Web Text)

Max Activating Token Index: 634

Text #14

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6750. Min Act: -0.1700

Data Index: 6583309 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6654. Min Act: -0.1700

Data Index: 2600874 (Open Web Text)

Max Activating Token Index: 318

Text #16

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6833. Min Act: -0.1700

Data Index: 8321635 (Open Web Text)

Max Activating Token Index: 715

Text #17

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6748. Min Act: -0.1700

Data Index: 339618 (Open Web Text)

Max Activating Token Index: 538

Text #18

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6751. Min Act: -0.1700

Data Index: 3272565 (Open Web Text)

Max Activating Token Index: 116

Text #19

Max Range: 2.7701. Min Range: -2.7701

Max Act: 2.6686. Min Act: -0.1700

Data Index: 1377293 (Open Web Text)

Max Activating Token Index: 732