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

Dataset: Open Web Text

Neuron 340 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: 0.9116. Min Range: -0.9116

Max Act: 0.9033. Min Act: -0.1700

Data Index: 5972122 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.9116. Min Act: -0.1700

Data Index: 5945866 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.9016. Min Act: -0.1700

Data Index: 2219469 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.9042. Min Act: -0.1700

Data Index: 336115 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8967. Min Act: -0.1700

Data Index: 5411000 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8936. Min Act: -0.1700

Data Index: 5377318 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8859. Min Act: -0.1700

Data Index: 1598743 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.9001. Min Act: -0.1700

Data Index: 3194204 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8935. Min Act: -0.1700

Data Index: 3500477 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8897. Min Act: -0.1700

Data Index: 5078276 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8931. Min Act: -0.1700

Data Index: 541745 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8853. Min Act: -0.1700

Data Index: 1178520 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8849. Min Act: -0.1700

Data Index: 7520951 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8837. Min Act: -0.1700

Data Index: 6644332 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8783. Min Act: -0.1700

Data Index: 5601499 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8862. Min Act: -0.1700

Data Index: 4630553 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8849. Min Act: -0.1700

Data Index: 6419799 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8837. Min Act: -0.1700

Data Index: 7049009 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8848. Min Act: -0.1700

Data Index: 3521881 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8804. Min Act: -0.1700

Data Index: 3508233 (Open Web Text)

Max Activating Token Index: 2