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

Dataset: Open Web Text

Neuron 1900 in Layer 1

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: 1.7869. Min Range: -1.7869

Max Act: 1.7869. Min Act: -0.1692

Data Index: 277988 (Open Web Text)

Max Activating Token Index: 527

Text #1

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7720. Min Act: -0.1700

Data Index: 1022670 (Open Web Text)

Max Activating Token Index: 217

Text #2

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7604. Min Act: -0.1700

Data Index: 3845487 (Open Web Text)

Max Activating Token Index: 640

Text #3

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7498. Min Act: -0.1700

Data Index: 6598262 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7500. Min Act: -0.1700

Data Index: 4867767 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7490. Min Act: -0.1700

Data Index: 5771078 (Open Web Text)

Max Activating Token Index: 174

Text #6

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7448. Min Act: -0.1700

Data Index: 7307104 (Open Web Text)

Max Activating Token Index: 82

Text #7

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7332. Min Act: -0.1700

Data Index: 5381740 (Open Web Text)

Max Activating Token Index: 206

Text #8

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7170. Min Act: -0.1700

Data Index: 5393566 (Open Web Text)

Max Activating Token Index: 531

Text #9

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7120. Min Act: -0.1700

Data Index: 3493622 (Open Web Text)

Max Activating Token Index: 259

Text #10

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7049. Min Act: -0.1700

Data Index: 1446054 (Open Web Text)

Max Activating Token Index: 212

Text #11

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7092. Min Act: -0.1700

Data Index: 3200941 (Open Web Text)

Max Activating Token Index: 475

Text #12

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6854. Min Act: -0.1700

Data Index: 1486770 (Open Web Text)

Max Activating Token Index: 748

Text #13

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6982. Min Act: -0.1700

Data Index: 4339139 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6842. Min Act: -0.1700

Data Index: 6498082 (Open Web Text)

Max Activating Token Index: 92

Text #15

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6880. Min Act: -0.1700

Data Index: 7080703 (Open Web Text)

Max Activating Token Index: 400

Text #16

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6863. Min Act: -0.1700

Data Index: 618721 (Open Web Text)

Max Activating Token Index: 762

Text #17

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6853. Min Act: -0.1700

Data Index: 1291703 (Open Web Text)

Max Activating Token Index: 798

Text #18

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6947. Min Act: -0.1700

Data Index: 315552 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.6800. Min Act: -0.1700

Data Index: 556930 (Open Web Text)

Max Activating Token Index: 248