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

Dataset: Open Web Text

Neuron 2433 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: 3.9237. Min Range: -3.9237

Max Act: 3.9237. Min Act: -0.1700

Data Index: 7051292 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.8726. Min Act: -0.1700

Data Index: 3619975 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.8394. Min Act: -0.1700

Data Index: 7257788 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.8331. Min Act: -0.1700

Data Index: 8540786 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7638. Min Act: -0.1700

Data Index: 2747056 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7619. Min Act: -0.1700

Data Index: 5758322 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7753. Min Act: -0.1700

Data Index: 4260946 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7694. Min Act: -0.1700

Data Index: 8028699 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7456. Min Act: -0.1700

Data Index: 4365639 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7489. Min Act: -0.1700

Data Index: 2691167 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7256. Min Act: -0.1700

Data Index: 5198085 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7309. Min Act: -0.1700

Data Index: 3954908 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7248. Min Act: -0.1700

Data Index: 3099645 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7518. Min Act: -0.1700

Data Index: 6099865 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7332. Min Act: -0.1700

Data Index: 4237407 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7283. Min Act: -0.1700

Data Index: 5312962 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.6998. Min Act: -0.1700

Data Index: 4524179 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7003. Min Act: -0.1700

Data Index: 5014182 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.7216. Min Act: -0.1700

Data Index: 5020768 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.6968. Min Act: -0.1700

Data Index: 2646292 (Open Web Text)

Max Activating Token Index: 6