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

Dataset: Open Web Text

Neuron 2248 in Layer 4

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: 4.0746. Min Range: -4.0746

Max Act: 4.0746. Min Act: -0.1700

Data Index: 8325813 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9789. Min Act: -0.1700

Data Index: 8776684 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9906. Min Act: -0.1700

Data Index: 4755 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9917. Min Act: -0.1700

Data Index: 408404 (Open Web Text)

Max Activating Token Index: 111

Text #4

Max Range: 4.0746. Min Range: -4.0746

Max Act: 4.0202. Min Act: -0.1700

Data Index: 3828391 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9692. Min Act: -0.1700

Data Index: 186088 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9855. Min Act: -0.1700

Data Index: 3919233 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9339. Min Act: -0.1700

Data Index: 1321210 (Open Web Text)

Max Activating Token Index: 753

Text #8

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9422. Min Act: -0.1700

Data Index: 5620380 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8886. Min Act: -0.1700

Data Index: 1170111 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8893. Min Act: -0.1700

Data Index: 5028141 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8855. Min Act: -0.1700

Data Index: 948541 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8991. Min Act: -0.1700

Data Index: 399090 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9016. Min Act: -0.1700

Data Index: 8653060 (Open Web Text)

Max Activating Token Index: 667

Text #14

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9242. Min Act: -0.1700

Data Index: 3164148 (Open Web Text)

Max Activating Token Index: 119

Text #15

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8899. Min Act: -0.1700

Data Index: 1331593 (Open Web Text)

Max Activating Token Index: 320

Text #16

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9153. Min Act: -0.1700

Data Index: 5670426 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8802. Min Act: -0.1700

Data Index: 4333973 (Open Web Text)

Max Activating Token Index: 836

Text #18

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8642. Min Act: -0.1700

Data Index: 5202264 (Open Web Text)

Max Activating Token Index: 320

Text #19

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8824. Min Act: -0.1700

Data Index: 3438606 (Open Web Text)

Max Activating Token Index: 846