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

Dataset: Open Web Text

Neuron 314 in Layer 3

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: 3.7531. Min Range: -3.7531

Max Act: 3.7531. Min Act: -0.1700

Data Index: 2948254 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.7377. Min Act: -0.1700

Data Index: 1811344 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.6975. Min Act: -0.1700

Data Index: 7862715 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.6219. Min Act: -0.1700

Data Index: 5680674 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.5660. Min Act: -0.1700

Data Index: 5102715 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.5526. Min Act: -0.1700

Data Index: 1359701 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.5218. Min Act: -0.1700

Data Index: 6046635 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.5232. Min Act: -0.1700

Data Index: 3628738 (Open Web Text)

Max Activating Token Index: 590

Text #8

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.5337. Min Act: -0.1700

Data Index: 3563259 (Open Web Text)

Max Activating Token Index: 325

Text #9

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.5416. Min Act: -0.1700

Data Index: 3534961 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4599. Min Act: -0.1700

Data Index: 8010833 (Open Web Text)

Max Activating Token Index: 76

Text #11

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4634. Min Act: -0.1700

Data Index: 6554108 (Open Web Text)

Max Activating Token Index: 922

Text #12

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4615. Min Act: -0.1700

Data Index: 454665 (Open Web Text)

Max Activating Token Index: 77

Text #13

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4742. Min Act: -0.1700

Data Index: 6425136 (Open Web Text)

Max Activating Token Index: 677

Text #14

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4410. Min Act: -0.1700

Data Index: 1571526 (Open Web Text)

Max Activating Token Index: 215

Text #15

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4718. Min Act: -0.1700

Data Index: 514972 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4563. Min Act: -0.1700

Data Index: 1394098 (Open Web Text)

Max Activating Token Index: 93

Text #17

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4349. Min Act: -0.1700

Data Index: 7301091 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4402. Min Act: -0.1700

Data Index: 1006537 (Open Web Text)

Max Activating Token Index: 990

Text #19

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4236. Min Act: -0.1700

Data Index: 2442338 (Open Web Text)

Max Activating Token Index: 694