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

Dataset: Open Web Text

Neuron 2077 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: 2.5764. Min Range: -2.5764

Max Act: 2.5764. Min Act: -0.1700

Data Index: 7444246 (Open Web Text)

Max Activating Token Index: 142

Text #1

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5345. Min Act: -0.1700

Data Index: 6026328 (Open Web Text)

Max Activating Token Index: 266

Text #2

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5266. Min Act: -0.1700

Data Index: 7840790 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5201. Min Act: -0.1700

Data Index: 1342108 (Open Web Text)

Max Activating Token Index: 820

Text #4

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5264. Min Act: -0.1700

Data Index: 1486192 (Open Web Text)

Max Activating Token Index: 248

Text #5

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5231. Min Act: -0.1700

Data Index: 6277243 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5037. Min Act: -0.1700

Data Index: 5176782 (Open Web Text)

Max Activating Token Index: 332

Text #7

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5000. Min Act: -0.1700

Data Index: 3622507 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.4960. Min Act: -0.1700

Data Index: 55774 (Open Web Text)

Max Activating Token Index: 893

Text #9

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5039. Min Act: -0.1700

Data Index: 3334174 (Open Web Text)

Max Activating Token Index: 313

Text #10

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5006. Min Act: -0.1700

Data Index: 5867072 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5020. Min Act: -0.1700

Data Index: 3023032 (Open Web Text)

Max Activating Token Index: 335

Text #12

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5035. Min Act: -0.1700

Data Index: 6702744 (Open Web Text)

Max Activating Token Index: 226

Text #13

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.4825. Min Act: -0.1700

Data Index: 7590932 (Open Web Text)

Max Activating Token Index: 272

Text #14

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.4929. Min Act: -0.1700

Data Index: 3761389 (Open Web Text)

Max Activating Token Index: 27

Text #15

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.4877. Min Act: -0.1700

Data Index: 4598059 (Open Web Text)

Max Activating Token Index: 181

Text #16

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.4944. Min Act: -0.1700

Data Index: 2891482 (Open Web Text)

Max Activating Token Index: 285

Text #17

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.4950. Min Act: -0.1700

Data Index: 4939422 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.4889. Min Act: -0.1700

Data Index: 6996795 (Open Web Text)

Max Activating Token Index: 423

Text #19

Max Range: 2.5764. Min Range: -2.5764

Max Act: 2.5060. Min Act: -0.1700

Data Index: 8498719 (Open Web Text)

Max Activating Token Index: 704