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

Dataset: Open Web Text

Neuron 654 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: 3.4116. Min Range: -3.4116

Max Act: 3.4116. Min Act: -0.1700

Data Index: 4077055 (Open Web Text)

Max Activating Token Index: 1019

Text #1

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.2909. Min Act: -0.1700

Data Index: 8428557 (Open Web Text)

Max Activating Token Index: 1004

Text #2

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.2697. Min Act: -0.1700

Data Index: 8366897 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.2255. Min Act: -0.1700

Data Index: 1486820 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1942. Min Act: -0.1700

Data Index: 2593677 (Open Web Text)

Max Activating Token Index: 622

Text #5

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1750. Min Act: -0.1700

Data Index: 7405130 (Open Web Text)

Max Activating Token Index: 99

Text #6

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1865. Min Act: -0.1700

Data Index: 7353374 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1568. Min Act: -0.1700

Data Index: 1475287 (Open Web Text)

Max Activating Token Index: 872

Text #8

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1572. Min Act: -0.1700

Data Index: 5401591 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1665. Min Act: -0.1700

Data Index: 746364 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1393. Min Act: -0.1700

Data Index: 3608269 (Open Web Text)

Max Activating Token Index: 509

Text #11

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1505. Min Act: -0.1700

Data Index: 6939747 (Open Web Text)

Max Activating Token Index: 564

Text #12

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1255. Min Act: -0.1700

Data Index: 617361 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1499. Min Act: -0.1700

Data Index: 7170814 (Open Web Text)

Max Activating Token Index: 467

Text #14

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1420. Min Act: -0.1700

Data Index: 399186 (Open Web Text)

Max Activating Token Index: 318

Text #15

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1265. Min Act: -0.1700

Data Index: 3029242 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1237. Min Act: -0.1700

Data Index: 8546432 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1285. Min Act: -0.1700

Data Index: 1675181 (Open Web Text)

Max Activating Token Index: 312

Text #18

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1422. Min Act: -0.1700

Data Index: 8198135 (Open Web Text)

Max Activating Token Index: 428

Text #19

Max Range: 3.4116. Min Range: -3.4116

Max Act: 3.1180. Min Act: -0.1700

Data Index: 5454125 (Open Web Text)

Max Activating Token Index: 39