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

Dataset: Open Web Text

Neuron 784 in Layer 6

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: 3.1696. Min Range: -3.1696

Max Act: 3.1618. Min Act: -0.1700

Data Index: 4619099 (Open Web Text)

Max Activating Token Index: 594

Text #1

Max Range: 3.1696. Min Range: -3.1696

Max Act: 3.1696. Min Act: -0.1700

Data Index: 7947484 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 3.1696. Min Range: -3.1696

Max Act: 3.1427. Min Act: -0.1700

Data Index: 4801086 (Open Web Text)

Max Activating Token Index: 832

Text #3

Max Range: 3.1696. Min Range: -3.1696

Max Act: 3.1081. Min Act: -0.1700

Data Index: 1969311 (Open Web Text)

Max Activating Token Index: 525

Text #4

Max Range: 3.1696. Min Range: -3.1696

Max Act: 3.0745. Min Act: -0.1700

Data Index: 6680535 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 3.1696. Min Range: -3.1696

Max Act: 3.0272. Min Act: -0.1700

Data Index: 451193 (Open Web Text)

Max Activating Token Index: 521

Text #6

Max Range: 3.1696. Min Range: -3.1696

Max Act: 3.0160. Min Act: -0.1700

Data Index: 2233396 (Open Web Text)

Max Activating Token Index: 488

Text #7

Max Range: 3.1696. Min Range: -3.1696

Max Act: 3.0202. Min Act: -0.1700

Data Index: 4721443 (Open Web Text)

Max Activating Token Index: 469

Text #8

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9929. Min Act: -0.1700

Data Index: 5652400 (Open Web Text)

Max Activating Token Index: 365

Text #9

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9766. Min Act: -0.1700

Data Index: 2235556 (Open Web Text)

Max Activating Token Index: 487

Text #10

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9823. Min Act: -0.1700

Data Index: 2752412 (Open Web Text)

Max Activating Token Index: 375

Text #11

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9749. Min Act: -0.1700

Data Index: 1134539 (Open Web Text)

Max Activating Token Index: 561

Text #12

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9525. Min Act: -0.1700

Data Index: 6097003 (Open Web Text)

Max Activating Token Index: 62

Text #13

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9740. Min Act: -0.1700

Data Index: 7888837 (Open Web Text)

Max Activating Token Index: 827

Text #14

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9410. Min Act: -0.1700

Data Index: 764832 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9280. Min Act: -0.1700

Data Index: 710263 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9305. Min Act: -0.1700

Data Index: 3635504 (Open Web Text)

Max Activating Token Index: 1014

Text #17

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9422. Min Act: -0.1700

Data Index: 5582449 (Open Web Text)

Max Activating Token Index: 237

Text #18

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9355. Min Act: -0.1700

Data Index: 6280150 (Open Web Text)

Max Activating Token Index: 575

Text #19

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.9308. Min Act: -0.1700

Data Index: 4518168 (Open Web Text)

Max Activating Token Index: 837