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

Dataset: Open Web Text

Neuron 2166 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: 4.0719. Min Range: -4.0719

Max Act: 4.0719. Min Act: -0.1700

Data Index: 7762466 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.0719. Min Range: -4.0719

Max Act: 4.0595. Min Act: -0.1700

Data Index: 8236009 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.0719. Min Range: -4.0719

Max Act: 4.0523. Min Act: -0.1700

Data Index: 325948 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0719. Min Range: -4.0719

Max Act: 4.0107. Min Act: -0.1700

Data Index: 1175104 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0719. Min Range: -4.0719

Max Act: 4.0099. Min Act: -0.1700

Data Index: 1225777 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9879. Min Act: -0.1700

Data Index: 1783478 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9868. Min Act: -0.1700

Data Index: 6790221 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9899. Min Act: -0.1700

Data Index: 1771242 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9761. Min Act: -0.1700

Data Index: 1710644 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9939. Min Act: -0.1700

Data Index: 1030642 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9717. Min Act: -0.1700

Data Index: 3260356 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9446. Min Act: -0.1700

Data Index: 446852 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9492. Min Act: -0.1700

Data Index: 4450805 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9658. Min Act: -0.1700

Data Index: 4756909 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9444. Min Act: -0.1700

Data Index: 1308730 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9656. Min Act: -0.1700

Data Index: 5157430 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9522. Min Act: -0.1700

Data Index: 3105665 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9491. Min Act: -0.1700

Data Index: 2017666 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9499. Min Act: -0.1700

Data Index: 5346936 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9572. Min Act: -0.1700

Data Index: 5635725 (Open Web Text)

Max Activating Token Index: 8