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

Dataset: Open Web Text

Neuron 251 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: 5.0819. Min Range: -5.0819

Max Act: 5.0819. Min Act: -0.1700

Data Index: 1094918 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.9903. Min Act: -0.1700

Data Index: 5866144 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8868. Min Act: -0.1700

Data Index: 3002850 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.9116. Min Act: -0.1700

Data Index: 37284 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8628. Min Act: -0.1700

Data Index: 7602957 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 3381614 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 3546155 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 2908480 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 8383975 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 8046105 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8288. Min Act: -0.1700

Data Index: 4742714 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 6094991 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 3158029 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8575. Min Act: -0.1700

Data Index: 1925257 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8471. Min Act: -0.1700

Data Index: 7413840 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 347155 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8443. Min Act: -0.1700

Data Index: 6436688 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8260. Min Act: -0.1700

Data Index: 4386766 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8225. Min Act: -0.1700

Data Index: 3118949 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 5.0819. Min Range: -5.0819

Max Act: 4.8106. Min Act: -0.1700

Data Index: 4980814 (Open Web Text)

Max Activating Token Index: 7