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

Dataset: Open Web Text

Neuron 2145 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: 5.1345. Min Range: -5.1345

Max Act: 5.1345. Min Act: -0.1700

Data Index: 3959867 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0936. Min Act: -0.1700

Data Index: 5121936 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0862. Min Act: -0.1700

Data Index: 1922222 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0695. Min Act: -0.1700

Data Index: 5212115 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0834. Min Act: -0.1700

Data Index: 3867074 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0326. Min Act: -0.1700

Data Index: 4175912 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0497. Min Act: -0.1700

Data Index: 6432108 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0191. Min Act: -0.1700

Data Index: 5169524 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0029. Min Act: -0.1700

Data Index: 5194491 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0277. Min Act: -0.1700

Data Index: 5731797 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0105. Min Act: -0.1700

Data Index: 7618175 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9689. Min Act: -0.1700

Data Index: 8681180 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9775. Min Act: -0.1700

Data Index: 8139216 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9908. Min Act: -0.1700

Data Index: 3157594 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9659. Min Act: -0.1700

Data Index: 3887464 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9868. Min Act: -0.1700

Data Index: 3015736 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9829. Min Act: -0.1700

Data Index: 6038877 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9834. Min Act: -0.1700

Data Index: 2901845 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9728. Min Act: -0.1700

Data Index: 163523 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 5.1345. Min Range: -5.1345

Max Act: 4.9797. Min Act: -0.1700

Data Index: 3597335 (Open Web Text)

Max Activating Token Index: 12