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

Dataset: Open Web Text

Neuron 1906 in Layer 5

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: 4.4623. Min Range: -4.4623

Max Act: 4.4623. Min Act: -0.1700

Data Index: 6780408 (Open Web Text)

Max Activating Token Index: 176

Text #1

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.4024. Min Act: -0.1700

Data Index: 4633103 (Open Web Text)

Max Activating Token Index: 942

Text #2

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.3694. Min Act: -0.1700

Data Index: 8167691 (Open Web Text)

Max Activating Token Index: 731

Text #3

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.3445. Min Act: -0.1700

Data Index: 7529446 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.3002. Min Act: -0.1700

Data Index: 251587 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.3306. Min Act: -0.1700

Data Index: 3435035 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2896. Min Act: -0.1700

Data Index: 2513526 (Open Web Text)

Max Activating Token Index: 75

Text #7

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2701. Min Act: -0.1700

Data Index: 3773259 (Open Web Text)

Max Activating Token Index: 480

Text #8

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2834. Min Act: -0.1700

Data Index: 5192477 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2511. Min Act: -0.1700

Data Index: 4368326 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2400. Min Act: -0.1700

Data Index: 5940326 (Open Web Text)

Max Activating Token Index: 146

Text #11

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2399. Min Act: -0.1700

Data Index: 6597362 (Open Web Text)

Max Activating Token Index: 287

Text #12

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2185. Min Act: -0.1700

Data Index: 8349175 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2275. Min Act: -0.1700

Data Index: 3930329 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.1758. Min Act: -0.1700

Data Index: 6816913 (Open Web Text)

Max Activating Token Index: 509

Text #15

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.2216. Min Act: -0.1700

Data Index: 1525739 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.1664. Min Act: -0.1700

Data Index: 5743472 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.1762. Min Act: -0.1700

Data Index: 5798900 (Open Web Text)

Max Activating Token Index: 590

Text #18

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.1956. Min Act: -0.1700

Data Index: 6874037 (Open Web Text)

Max Activating Token Index: 459

Text #19

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.1994. Min Act: -0.1700

Data Index: 6986213 (Open Web Text)

Max Activating Token Index: 553