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

Dataset: Open Web Text

Neuron 1970 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: 3.0284. Min Range: -3.0284

Max Act: 3.0284. Min Act: -0.1700

Data Index: 7296126 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.0284. Min Range: -3.0284

Max Act: 3.0116. Min Act: -0.1700

Data Index: 5266601 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.0284. Min Range: -3.0284

Max Act: 3.0077. Min Act: -0.1700

Data Index: 7962199 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.0284. Min Range: -3.0284

Max Act: 3.0081. Min Act: -0.1700

Data Index: 5710540 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.0284. Min Range: -3.0284

Max Act: 3.0119. Min Act: -0.1700

Data Index: 8562719 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9886. Min Act: -0.1700

Data Index: 7405206 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9563. Min Act: -0.1700

Data Index: 341545 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9611. Min Act: -0.1700

Data Index: 7051226 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9571. Min Act: -0.1700

Data Index: 653051 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9558. Min Act: -0.1700

Data Index: 8233108 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9568. Min Act: -0.1700

Data Index: 4508347 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9403. Min Act: -0.1700

Data Index: 4728713 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9417. Min Act: -0.1700

Data Index: 328954 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9421. Min Act: -0.1700

Data Index: 3059177 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9399. Min Act: -0.1700

Data Index: 4616522 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9484. Min Act: -0.1700

Data Index: 2323263 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9487. Min Act: -0.1700

Data Index: 3465351 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9513. Min Act: -0.1700

Data Index: 486346 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9446. Min Act: -0.1700

Data Index: 3374846 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9263. Min Act: -0.1700

Data Index: 4366847 (Open Web Text)

Max Activating Token Index: 4