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

Dataset: Open Web Text

Neuron 587 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: 3.6331. Min Range: -3.6331

Max Act: 3.6331. Min Act: -0.1700

Data Index: 2551159 (Open Web Text)

Max Activating Token Index: 193

Text #1

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5612. Min Act: -0.1700

Data Index: 2791939 (Open Web Text)

Max Activating Token Index: 687

Text #2

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5412. Min Act: -0.1700

Data Index: 2080002 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5279. Min Act: -0.1700

Data Index: 6861489 (Open Web Text)

Max Activating Token Index: 688

Text #4

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5388. Min Act: -0.1700

Data Index: 7835762 (Open Web Text)

Max Activating Token Index: 106

Text #5

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.5178. Min Act: -0.1700

Data Index: 3140244 (Open Web Text)

Max Activating Token Index: 454

Text #6

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4930. Min Act: -0.1700

Data Index: 3620696 (Open Web Text)

Max Activating Token Index: 330

Text #7

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4889. Min Act: -0.1700

Data Index: 7100326 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4959. Min Act: -0.1700

Data Index: 4015393 (Open Web Text)

Max Activating Token Index: 66

Text #9

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4803. Min Act: -0.1700

Data Index: 6241462 (Open Web Text)

Max Activating Token Index: 179

Text #10

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4929. Min Act: -0.1700

Data Index: 4213274 (Open Web Text)

Max Activating Token Index: 547

Text #11

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4835. Min Act: -0.1700

Data Index: 294507 (Open Web Text)

Max Activating Token Index: 746

Text #12

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4682. Min Act: -0.1700

Data Index: 7015745 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4700. Min Act: -0.1700

Data Index: 4495942 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4502. Min Act: -0.1700

Data Index: 6973048 (Open Web Text)

Max Activating Token Index: 130

Text #15

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4518. Min Act: -0.1700

Data Index: 5169195 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4373. Min Act: -0.1700

Data Index: 2201713 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4311. Min Act: -0.1700

Data Index: 8560986 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4308. Min Act: -0.1700

Data Index: 6591637 (Open Web Text)

Max Activating Token Index: 679

Text #19

Max Range: 3.6331. Min Range: -3.6331

Max Act: 3.4249. Min Act: -0.1700

Data Index: 6429429 (Open Web Text)

Max Activating Token Index: 173