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

Dataset: Open Web Text

Neuron 1870 in Layer 3

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: 4.4375. Min Range: -4.4375

Max Act: 4.4375. Min Act: -0.1700

Data Index: 3511230 (Open Web Text)

Max Activating Token Index: 294

Text #1

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.2604. Min Act: -0.1700

Data Index: 8022594 (Open Web Text)

Max Activating Token Index: 809

Text #2

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.1676. Min Act: -0.1700

Data Index: 3990559 (Open Web Text)

Max Activating Token Index: 86

Text #3

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.1427. Min Act: -0.1700

Data Index: 1880450 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.1197. Min Act: -0.1700

Data Index: 209624 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.1251. Min Act: -0.1700

Data Index: 6099727 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.1075. Min Act: -0.1700

Data Index: 7765963 (Open Web Text)

Max Activating Token Index: 416

Text #7

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.0019. Min Act: -0.1700

Data Index: 741820 (Open Web Text)

Max Activating Token Index: 680

Text #8

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.0105. Min Act: -0.1700

Data Index: 1982959 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9999. Min Act: -0.1700

Data Index: 3476782 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9939. Min Act: -0.1700

Data Index: 7256721 (Open Web Text)

Max Activating Token Index: 373

Text #11

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9974. Min Act: -0.1700

Data Index: 1176367 (Open Web Text)

Max Activating Token Index: 183

Text #12

Max Range: 4.4375. Min Range: -4.4375

Max Act: 4.0100. Min Act: -0.1700

Data Index: 2860819 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9609. Min Act: -0.1700

Data Index: 1843426 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9550. Min Act: -0.1700

Data Index: 3160594 (Open Web Text)

Max Activating Token Index: 838

Text #15

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9562. Min Act: -0.1700

Data Index: 1497460 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9587. Min Act: -0.1700

Data Index: 3332021 (Open Web Text)

Max Activating Token Index: 155

Text #17

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9786. Min Act: -0.1700

Data Index: 7353303 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9507. Min Act: -0.1700

Data Index: 970926 (Open Web Text)

Max Activating Token Index: 293

Text #19

Max Range: 4.4375. Min Range: -4.4375

Max Act: 3.9264. Min Act: -0.1700

Data Index: 2394354 (Open Web Text)

Max Activating Token Index: 394