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

Dataset: Open Web Text

Neuron 843 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: 4.3927. Min Range: -4.3927

Max Act: 4.3927. Min Act: -0.1700

Data Index: 5432647 (Open Web Text)

Max Activating Token Index: 798

Text #1

Max Range: 4.3927. Min Range: -4.3927

Max Act: 4.1668. Min Act: -0.1700

Data Index: 7068751 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 4.3927. Min Range: -4.3927

Max Act: 4.0646. Min Act: -0.1700

Data Index: 935000 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 4.3927. Min Range: -4.3927

Max Act: 4.0429. Min Act: -0.1700

Data Index: 5417544 (Open Web Text)

Max Activating Token Index: 511

Text #4

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.9312. Min Act: -0.1700

Data Index: 4582624 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.9321. Min Act: -0.1700

Data Index: 5233178 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.8805. Min Act: -0.1700

Data Index: 4084612 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.8984. Min Act: -0.1700

Data Index: 2199975 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.8662. Min Act: -0.1700

Data Index: 7131049 (Open Web Text)

Max Activating Token Index: 730

Text #9

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.8135. Min Act: -0.1700

Data Index: 8217504 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.8351. Min Act: -0.1700

Data Index: 4782485 (Open Web Text)

Max Activating Token Index: 835

Text #11

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.7785. Min Act: -0.1700

Data Index: 6966545 (Open Web Text)

Max Activating Token Index: 979

Text #12

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.7835. Min Act: -0.1700

Data Index: 256064 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.8038. Min Act: -0.1700

Data Index: 294689 (Open Web Text)

Max Activating Token Index: 313

Text #14

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.7858. Min Act: -0.1700

Data Index: 104118 (Open Web Text)

Max Activating Token Index: 518

Text #15

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.7789. Min Act: -0.1700

Data Index: 6907893 (Open Web Text)

Max Activating Token Index: 695

Text #16

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.7519. Min Act: -0.1700

Data Index: 3480841 (Open Web Text)

Max Activating Token Index: 343

Text #17

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.7327. Min Act: -0.1700

Data Index: 5974773 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.7352. Min Act: -0.1700

Data Index: 5752474 (Open Web Text)

Max Activating Token Index: 843

Text #19

Max Range: 4.3927. Min Range: -4.3927

Max Act: 3.7415. Min Act: -0.1700

Data Index: 3077201 (Open Web Text)

Max Activating Token Index: 844