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

Dataset: Open Web Text

Neuron 2143 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: 3.2382. Min Range: -3.2382

Max Act: 3.2382. Min Act: -0.1700

Data Index: 8639876 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.2334. Min Act: -0.1700

Data Index: 3005880 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.2057. Min Act: -0.1700

Data Index: 1134370 (Open Web Text)

Max Activating Token Index: 384

Text #3

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.2075. Min Act: -0.1700

Data Index: 2537082 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.2084. Min Act: -0.1700

Data Index: 7450375 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.2037. Min Act: -0.1700

Data Index: 5073475 (Open Web Text)

Max Activating Token Index: 777

Text #6

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1937. Min Act: -0.1700

Data Index: 5891298 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1951. Min Act: -0.1700

Data Index: 6265757 (Open Web Text)

Max Activating Token Index: 768

Text #8

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1924. Min Act: -0.1700

Data Index: 3848706 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1867. Min Act: -0.1700

Data Index: 4334645 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1882. Min Act: -0.1700

Data Index: 7248789 (Open Web Text)

Max Activating Token Index: 897

Text #11

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1930. Min Act: -0.1700

Data Index: 2351867 (Open Web Text)

Max Activating Token Index: 472

Text #12

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1891. Min Act: -0.1700

Data Index: 4767542 (Open Web Text)

Max Activating Token Index: 329

Text #13

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1872. Min Act: -0.1700

Data Index: 3058927 (Open Web Text)

Max Activating Token Index: 984

Text #14

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1781. Min Act: -0.1700

Data Index: 975122 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1720. Min Act: -0.1700

Data Index: 5028412 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1568. Min Act: -0.1700

Data Index: 7833035 (Open Web Text)

Max Activating Token Index: 291

Text #17

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1912. Min Act: -0.1700

Data Index: 2888355 (Open Web Text)

Max Activating Token Index: 911

Text #18

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1757. Min Act: -0.1700

Data Index: 4049389 (Open Web Text)

Max Activating Token Index: 892

Text #19

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1713. Min Act: -0.1700

Data Index: 7960002 (Open Web Text)

Max Activating Token Index: 548