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

Dataset: Open Web Text

Neuron 1457 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: 4.2738. Min Range: -4.2738

Max Act: 4.2615. Min Act: -0.1700

Data Index: 2605181 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.2378. Min Act: -0.1700

Data Index: 596356 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.2222. Min Act: -0.1700

Data Index: 6080676 (Open Web Text)

Max Activating Token Index: 547

Text #3

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.2738. Min Act: -0.1700

Data Index: 2703916 (Open Web Text)

Max Activating Token Index: 445

Text #4

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.2135. Min Act: -0.1700

Data Index: 92739 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1820. Min Act: -0.1700

Data Index: 5306230 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1821. Min Act: -0.1700

Data Index: 5092489 (Open Web Text)

Max Activating Token Index: 816

Text #7

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.2089. Min Act: -0.1700

Data Index: 5014548 (Open Web Text)

Max Activating Token Index: 660

Text #8

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.2097. Min Act: -0.1700

Data Index: 879986 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1671. Min Act: -0.1700

Data Index: 6313671 (Open Web Text)

Max Activating Token Index: 759

Text #10

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1724. Min Act: -0.1700

Data Index: 8664420 (Open Web Text)

Max Activating Token Index: 859

Text #11

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1875. Min Act: -0.1700

Data Index: 7148071 (Open Web Text)

Max Activating Token Index: 318

Text #12

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1927. Min Act: -0.1700

Data Index: 7000370 (Open Web Text)

Max Activating Token Index: 473

Text #13

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1784. Min Act: -0.1700

Data Index: 6863841 (Open Web Text)

Max Activating Token Index: 801

Text #14

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1961. Min Act: -0.1700

Data Index: 101033 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1826. Min Act: -0.1700

Data Index: 6746524 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1434. Min Act: -0.1700

Data Index: 3417164 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1069. Min Act: -0.1700

Data Index: 4487564 (Open Web Text)

Max Activating Token Index: 563

Text #18

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1943. Min Act: -0.1700

Data Index: 4934515 (Open Web Text)

Max Activating Token Index: 719

Text #19

Max Range: 4.2738. Min Range: -4.2738

Max Act: 4.1520. Min Act: -0.1700

Data Index: 2335246 (Open Web Text)

Max Activating Token Index: 38