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

Dataset: Open Web Text

Neuron 2423 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: 4.1361. Min Range: -4.1361

Max Act: 4.1361. Min Act: -0.1700

Data Index: 4635504 (Open Web Text)

Max Activating Token Index: 571

Text #1

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.9792. Min Act: -0.1700

Data Index: 742563 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.9434. Min Act: -0.1700

Data Index: 4837340 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.9394. Min Act: -0.1700

Data Index: 573575 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.9394. Min Act: -0.1700

Data Index: 2560866 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.9068. Min Act: -0.1700

Data Index: 428388 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.9218. Min Act: -0.1700

Data Index: 2457749 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.9477. Min Act: -0.1700

Data Index: 5038310 (Open Web Text)

Max Activating Token Index: 393

Text #8

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8530. Min Act: -0.1700

Data Index: 5500086 (Open Web Text)

Max Activating Token Index: 748

Text #9

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8905. Min Act: -0.1700

Data Index: 8259749 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8918. Min Act: -0.1700

Data Index: 8175812 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8631. Min Act: -0.1700

Data Index: 4466887 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8829. Min Act: -0.1700

Data Index: 3282008 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.9310. Min Act: -0.1700

Data Index: 8023029 (Open Web Text)

Max Activating Token Index: 523

Text #14

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8701. Min Act: -0.1700

Data Index: 4074581 (Open Web Text)

Max Activating Token Index: 971

Text #15

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8267. Min Act: -0.1700

Data Index: 6705580 (Open Web Text)

Max Activating Token Index: 878

Text #16

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8207. Min Act: -0.1700

Data Index: 5249995 (Open Web Text)

Max Activating Token Index: 596

Text #17

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.7861. Min Act: -0.1700

Data Index: 3978213 (Open Web Text)

Max Activating Token Index: 305

Text #18

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.8402. Min Act: -0.1700

Data Index: 5795621 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 4.1361. Min Range: -4.1361

Max Act: 3.7937. Min Act: -0.1700

Data Index: 6358834 (Open Web Text)

Max Activating Token Index: 3