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

Dataset: Open Web Text

Neuron 1429 in Layer 1

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: 6.7038. Min Range: -6.7038

Max Act: 6.7038. Min Act: -0.1700

Data Index: 2977020 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.6852. Min Act: -0.1700

Data Index: 8726325 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.6990. Min Act: -0.1700

Data Index: 7196401 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5976. Min Act: -0.1700

Data Index: 4411024 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.6021. Min Act: -0.1700

Data Index: 1820083 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5723. Min Act: -0.1700

Data Index: 4648197 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.6108. Min Act: -0.1700

Data Index: 3701478 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5819. Min Act: -0.1700

Data Index: 1454369 (Open Web Text)

Max Activating Token Index: 290

Text #8

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5842. Min Act: -0.1700

Data Index: 1063975 (Open Web Text)

Max Activating Token Index: 962

Text #9

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5167. Min Act: -0.1700

Data Index: 6715621 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5637. Min Act: -0.1700

Data Index: 6307381 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5315. Min Act: -0.1700

Data Index: 2602876 (Open Web Text)

Max Activating Token Index: 975

Text #12

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5286. Min Act: -0.1700

Data Index: 7595059 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5429. Min Act: -0.1700

Data Index: 5630896 (Open Web Text)

Max Activating Token Index: 959

Text #14

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5404. Min Act: -0.1700

Data Index: 2805694 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5551. Min Act: -0.1700

Data Index: 3348312 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5643. Min Act: -0.1700

Data Index: 1022065 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.4941. Min Act: -0.1700

Data Index: 1687282 (Open Web Text)

Max Activating Token Index: 670

Text #18

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.4800. Min Act: -0.1700

Data Index: 336973 (Open Web Text)

Max Activating Token Index: 912

Text #19

Max Range: 6.7038. Min Range: -6.7038

Max Act: 6.5322. Min Act: -0.1700

Data Index: 2972417 (Open Web Text)

Max Activating Token Index: 549