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

Dataset: Open Web Text

Neuron 667 in Layer 0

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: 4.9052. Min Range: -4.9052

Max Act: 4.9052. Min Act: -0.1700

Data Index: 1280857 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8953. Min Act: -0.1700

Data Index: 3038133 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8588. Min Act: -0.1700

Data Index: 8819279 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8616. Min Act: -0.1700

Data Index: 1786803 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8109. Min Act: -0.1700

Data Index: 6107318 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8298. Min Act: -0.1700

Data Index: 7727490 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8375. Min Act: -0.1700

Data Index: 1431256 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7875. Min Act: -0.1700

Data Index: 5444888 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8030. Min Act: -0.1700

Data Index: 5245895 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7923. Min Act: -0.1700

Data Index: 8113497 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7897. Min Act: -0.1700

Data Index: 8232079 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8070. Min Act: -0.1700

Data Index: 4889276 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.8008. Min Act: -0.1700

Data Index: 1767307 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7778. Min Act: -0.1700

Data Index: 7628375 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7707. Min Act: -0.1700

Data Index: 943556 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7858. Min Act: -0.1700

Data Index: 2837369 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7753. Min Act: -0.1700

Data Index: 4725946 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7688. Min Act: -0.1700

Data Index: 6840624 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7788. Min Act: -0.1700

Data Index: 2269917 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.9052. Min Range: -4.9052

Max Act: 4.7786. Min Act: -0.1700

Data Index: 2937577 (Open Web Text)

Max Activating Token Index: 3