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

Dataset: Open Web Text

Neuron 2262 in Layer 2

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: 5.6722. Min Range: -5.6722

Max Act: 5.6722. Min Act: -0.1700

Data Index: 7154877 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.5856. Min Act: -0.1700

Data Index: 6789033 (Open Web Text)

Max Activating Token Index: 426

Text #2

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.5570. Min Act: -0.1700

Data Index: 8447090 (Open Web Text)

Max Activating Token Index: 750

Text #3

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.5467. Min Act: -0.1700

Data Index: 5656179 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.5298. Min Act: -0.1700

Data Index: 767895 (Open Web Text)

Max Activating Token Index: 192

Text #5

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4877. Min Act: -0.1700

Data Index: 4309587 (Open Web Text)

Max Activating Token Index: 280

Text #6

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4950. Min Act: -0.1700

Data Index: 7522899 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4444. Min Act: -0.1700

Data Index: 2354318 (Open Web Text)

Max Activating Token Index: 462

Text #8

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4798. Min Act: -0.1700

Data Index: 4655285 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4166. Min Act: -0.1700

Data Index: 7395439 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4284. Min Act: -0.1700

Data Index: 7037908 (Open Web Text)

Max Activating Token Index: 476

Text #11

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4538. Min Act: -0.1700

Data Index: 245735 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4398. Min Act: -0.1700

Data Index: 735855 (Open Web Text)

Max Activating Token Index: 677

Text #13

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4396. Min Act: -0.1700

Data Index: 3721191 (Open Web Text)

Max Activating Token Index: 480

Text #14

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.3964. Min Act: -0.1700

Data Index: 2092815 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.3820. Min Act: -0.1700

Data Index: 6357631 (Open Web Text)

Max Activating Token Index: 561

Text #16

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4131. Min Act: -0.1700

Data Index: 6707452 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.3874. Min Act: -0.1700

Data Index: 5536015 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4079. Min Act: -0.1700

Data Index: 5832890 (Open Web Text)

Max Activating Token Index: 158

Text #19

Max Range: 5.6722. Min Range: -5.6722

Max Act: 5.4200. Min Act: -0.1700

Data Index: 6953176 (Open Web Text)

Max Activating Token Index: 590