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

Dataset: Open Web Text

Neuron 1655 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: 3.0026. Min Range: -3.0026

Max Act: 3.0026. Min Act: -0.1700

Data Index: 1380308 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9872. Min Act: -0.1700

Data Index: 909410 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9814. Min Act: -0.1700

Data Index: 4590189 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9718. Min Act: -0.1700

Data Index: 5321636 (Open Web Text)

Max Activating Token Index: 859

Text #4

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9682. Min Act: -0.1700

Data Index: 5292949 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9651. Min Act: -0.1700

Data Index: 7557164 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9562. Min Act: -0.1700

Data Index: 6873543 (Open Web Text)

Max Activating Token Index: 574

Text #7

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9643. Min Act: -0.1700

Data Index: 8342618 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9686. Min Act: -0.1700

Data Index: 4595924 (Open Web Text)

Max Activating Token Index: 521

Text #9

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9406. Min Act: -0.1700

Data Index: 2547534 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9515. Min Act: -0.1700

Data Index: 2045982 (Open Web Text)

Max Activating Token Index: 819

Text #11

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9410. Min Act: -0.1700

Data Index: 8064039 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9465. Min Act: -0.1700

Data Index: 8066929 (Open Web Text)

Max Activating Token Index: 622

Text #13

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9412. Min Act: -0.1700

Data Index: 2037874 (Open Web Text)

Max Activating Token Index: 839

Text #14

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9378. Min Act: -0.1700

Data Index: 6851840 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9249. Min Act: -0.1700

Data Index: 4301773 (Open Web Text)

Max Activating Token Index: 805

Text #16

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9305. Min Act: -0.1700

Data Index: 7454104 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9279. Min Act: -0.1700

Data Index: 8653251 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9241. Min Act: -0.1700

Data Index: 3503971 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9072. Min Act: -0.1700

Data Index: 5707446 (Open Web Text)

Max Activating Token Index: 683