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

Dataset: Open Web Text

Neuron 3014 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: 5.5068. Min Range: -5.5068

Max Act: 5.5068. Min Act: -0.1700

Data Index: 6405823 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4804. Min Act: -0.1699

Data Index: 6747342 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4805. Min Act: -0.1700

Data Index: 1686354 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4804. Min Act: -0.1700

Data Index: 7478818 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4784. Min Act: -0.1700

Data Index: 4672351 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4544. Min Act: -0.1700

Data Index: 4767042 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4576. Min Act: -0.1700

Data Index: 387896 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4576. Min Act: -0.1700

Data Index: 1393781 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4544. Min Act: -0.1700

Data Index: 5852861 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4148. Min Act: -0.1700

Data Index: 6980753 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4018. Min Act: -0.1699

Data Index: 968972 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4018. Min Act: -0.1700

Data Index: 8444271 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.3990. Min Act: -0.1700

Data Index: 891922 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.4082. Min Act: -0.1700

Data Index: 6741671 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.3768. Min Act: -0.1700

Data Index: 111621 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.3768. Min Act: -0.1700

Data Index: 2513648 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.3810. Min Act: -0.1700

Data Index: 3131924 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.3768. Min Act: -0.1700

Data Index: 5248883 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.3768. Min Act: -0.1700

Data Index: 2295739 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.5068. Min Range: -5.5068

Max Act: 5.3863. Min Act: -0.1700

Data Index: 5022625 (Open Web Text)

Max Activating Token Index: 3