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

Dataset: Open Web Text

Neuron 2029 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: 6.5396. Min Range: -6.5396

Max Act: 6.5396. Min Act: -0.1700

Data Index: 2884631 (Open Web Text)

Max Activating Token Index: 1018

Text #1

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.5094. Min Act: -0.1700

Data Index: 602112 (Open Web Text)

Max Activating Token Index: 950

Text #2

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.3489. Min Act: -0.1700

Data Index: 2268825 (Open Web Text)

Max Activating Token Index: 604

Text #3

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.3239. Min Act: -0.1700

Data Index: 1609682 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.2850. Min Act: -0.1700

Data Index: 1778517 (Open Web Text)

Max Activating Token Index: 458

Text #5

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.2284. Min Act: -0.1700

Data Index: 3440766 (Open Web Text)

Max Activating Token Index: 148

Text #6

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.2885. Min Act: -0.1700

Data Index: 3637872 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.1458. Min Act: -0.1700

Data Index: 5512742 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.1955. Min Act: -0.1700

Data Index: 7235299 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.1062. Min Act: -0.1700

Data Index: 8391327 (Open Web Text)

Max Activating Token Index: 456

Text #10

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.1262. Min Act: -0.1700

Data Index: 4863886 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.1387. Min Act: -0.1700

Data Index: 4391807 (Open Web Text)

Max Activating Token Index: 797

Text #12

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.0673. Min Act: -0.1700

Data Index: 4474337 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.0451. Min Act: -0.1700

Data Index: 3771978 (Open Web Text)

Max Activating Token Index: 645

Text #14

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.0588. Min Act: -0.1700

Data Index: 8182147 (Open Web Text)

Max Activating Token Index: 690

Text #15

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.1004. Min Act: -0.1700

Data Index: 8158302 (Open Web Text)

Max Activating Token Index: 953

Text #16

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.0639. Min Act: -0.1700

Data Index: 813230 (Open Web Text)

Max Activating Token Index: 875

Text #17

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.0053. Min Act: -0.1700

Data Index: 6599509 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 6.5396. Min Range: -6.5396

Max Act: 5.9389. Min Act: -0.1700

Data Index: 3754896 (Open Web Text)

Max Activating Token Index: 874

Text #19

Max Range: 6.5396. Min Range: -6.5396

Max Act: 6.0100. Min Act: -0.1700

Data Index: 1845030 (Open Web Text)

Max Activating Token Index: 274