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

Dataset: Open Web Text

Neuron 944 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: 2.4394. Min Range: -2.4394

Max Act: 2.4394. Min Act: -0.1700

Data Index: 6404639 (Open Web Text)

Max Activating Token Index: 257

Text #1

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.4077. Min Act: -0.1700

Data Index: 7856493 (Open Web Text)

Max Activating Token Index: 258

Text #2

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3987. Min Act: -0.1700

Data Index: 2547529 (Open Web Text)

Max Activating Token Index: 259

Text #3

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3879. Min Act: -0.1700

Data Index: 5127272 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3895. Min Act: -0.1700

Data Index: 3284766 (Open Web Text)

Max Activating Token Index: 258

Text #5

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3918. Min Act: -0.1700

Data Index: 6667507 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3886. Min Act: -0.1700

Data Index: 301214 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3856. Min Act: -0.1700

Data Index: 4993614 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3840. Min Act: -0.1700

Data Index: 3371418 (Open Web Text)

Max Activating Token Index: 258

Text #9

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3860. Min Act: -0.1700

Data Index: 4180791 (Open Web Text)

Max Activating Token Index: 265

Text #10

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3697. Min Act: -0.1700

Data Index: 1557684 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3685. Min Act: -0.1700

Data Index: 4204304 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3580. Min Act: -0.1700

Data Index: 6456657 (Open Web Text)

Max Activating Token Index: 260

Text #13

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3603. Min Act: -0.1700

Data Index: 6337914 (Open Web Text)

Max Activating Token Index: 271

Text #14

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3568. Min Act: -0.1700

Data Index: 2887171 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3616. Min Act: -0.1700

Data Index: 6193573 (Open Web Text)

Max Activating Token Index: 257

Text #16

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3592. Min Act: -0.1700

Data Index: 6187863 (Open Web Text)

Max Activating Token Index: 265

Text #17

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3645. Min Act: -0.1700

Data Index: 3650188 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3592. Min Act: -0.1700

Data Index: 6140795 (Open Web Text)

Max Activating Token Index: 260

Text #19

Max Range: 2.4394. Min Range: -2.4394

Max Act: 2.3662. Min Act: -0.1700

Data Index: 4824179 (Open Web Text)

Max Activating Token Index: 262