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

Dataset: Open Web Text

Neuron 1836 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: 4.8530. Min Range: -4.8530

Max Act: 4.8530. Min Act: -0.1700

Data Index: 1592922 (Open Web Text)

Max Activating Token Index: 348

Text #1

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7780. Min Act: -0.1700

Data Index: 2274233 (Open Web Text)

Max Activating Token Index: 347

Text #2

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7062. Min Act: -0.1700

Data Index: 7569560 (Open Web Text)

Max Activating Token Index: 479

Text #3

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7063. Min Act: -0.1700

Data Index: 6891147 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7019. Min Act: -0.1700

Data Index: 6814271 (Open Web Text)

Max Activating Token Index: 428

Text #5

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.7026. Min Act: -0.1700

Data Index: 946757 (Open Web Text)

Max Activating Token Index: 145

Text #6

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6886. Min Act: -0.1700

Data Index: 1415665 (Open Web Text)

Max Activating Token Index: 648

Text #7

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6790. Min Act: -0.1700

Data Index: 3610181 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6490. Min Act: -0.1700

Data Index: 5208330 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6695. Min Act: -0.1700

Data Index: 7401932 (Open Web Text)

Max Activating Token Index: 552

Text #10

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6699. Min Act: -0.1700

Data Index: 159436 (Open Web Text)

Max Activating Token Index: 902

Text #11

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6629. Min Act: -0.1700

Data Index: 3945286 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6760. Min Act: -0.1700

Data Index: 3788329 (Open Web Text)

Max Activating Token Index: 935

Text #13

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6855. Min Act: -0.1700

Data Index: 174116 (Open Web Text)

Max Activating Token Index: 353

Text #14

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6732. Min Act: -0.1700

Data Index: 7810058 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6778. Min Act: -0.1700

Data Index: 8375814 (Open Web Text)

Max Activating Token Index: 603

Text #16

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6661. Min Act: -0.1700

Data Index: 1813235 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6281. Min Act: -0.1700

Data Index: 8780562 (Open Web Text)

Max Activating Token Index: 306

Text #18

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6612. Min Act: -0.1700

Data Index: 1365113 (Open Web Text)

Max Activating Token Index: 196

Text #19

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.6914. Min Act: -0.1700

Data Index: 7062585 (Open Web Text)

Max Activating Token Index: 477