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

Dataset: Open Web Text

Neuron 26 in Layer 5

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: 3.8487. Min Range: -3.8487

Max Act: 3.8487. Min Act: -0.1700

Data Index: 897850 (Open Web Text)

Max Activating Token Index: 598

Text #1

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.8019. Min Act: -0.1700

Data Index: 2308932 (Open Web Text)

Max Activating Token Index: 456

Text #2

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6703. Min Act: -0.1700

Data Index: 1912631 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.7013. Min Act: -0.1700

Data Index: 2724920 (Open Web Text)

Max Activating Token Index: 379

Text #4

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6674. Min Act: -0.1700

Data Index: 5207912 (Open Web Text)

Max Activating Token Index: 687

Text #5

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6801. Min Act: -0.1700

Data Index: 2877612 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6630. Min Act: -0.1700

Data Index: 6649981 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6618. Min Act: -0.1700

Data Index: 5930526 (Open Web Text)

Max Activating Token Index: 777

Text #8

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6406. Min Act: -0.1700

Data Index: 4216424 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6599. Min Act: -0.1700

Data Index: 5524953 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6276. Min Act: -0.1700

Data Index: 4320217 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.5844. Min Act: -0.1700

Data Index: 5752371 (Open Web Text)

Max Activating Token Index: 829

Text #12

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6256. Min Act: -0.1700

Data Index: 2959373 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.5980. Min Act: -0.1700

Data Index: 4506548 (Open Web Text)

Max Activating Token Index: 205

Text #14

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6287. Min Act: -0.1700

Data Index: 3804961 (Open Web Text)

Max Activating Token Index: 339

Text #15

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6231. Min Act: -0.1700

Data Index: 6819366 (Open Web Text)

Max Activating Token Index: 109

Text #16

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6153. Min Act: -0.1700

Data Index: 5456714 (Open Web Text)

Max Activating Token Index: 412

Text #17

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.6050. Min Act: -0.1700

Data Index: 525919 (Open Web Text)

Max Activating Token Index: 794

Text #18

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.5784. Min Act: -0.1700

Data Index: 3439854 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 3.8487. Min Range: -3.8487

Max Act: 3.5873. Min Act: -0.1700

Data Index: 2776540 (Open Web Text)

Max Activating Token Index: 381