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

Dataset: Open Web Text

Neuron 1327 in Layer 1

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: 1.7670. Min Range: -1.7670

Max Act: 1.7670. Min Act: -0.1700

Data Index: 6217927 (Open Web Text)

Max Activating Token Index: 541

Text #1

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7411. Min Act: -0.1700

Data Index: 3334415 (Open Web Text)

Max Activating Token Index: 638

Text #2

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7497. Min Act: -0.1700

Data Index: 1463537 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7407. Min Act: -0.1700

Data Index: 3768763 (Open Web Text)

Max Activating Token Index: 725

Text #4

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7335. Min Act: -0.1700

Data Index: 3270747 (Open Web Text)

Max Activating Token Index: 922

Text #5

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7296. Min Act: -0.1700

Data Index: 4221257 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7235. Min Act: -0.1700

Data Index: 3506491 (Open Web Text)

Max Activating Token Index: 488

Text #7

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7262. Min Act: -0.1700

Data Index: 1627068 (Open Web Text)

Max Activating Token Index: 739

Text #8

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7237. Min Act: -0.1700

Data Index: 6905944 (Open Web Text)

Max Activating Token Index: 697

Text #9

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7283. Min Act: -0.1700

Data Index: 957326 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7147. Min Act: -0.1700

Data Index: 1330291 (Open Web Text)

Max Activating Token Index: 613

Text #11

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7148. Min Act: -0.1700

Data Index: 6593245 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7066. Min Act: -0.1700

Data Index: 3689605 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7017. Min Act: -0.1700

Data Index: 395783 (Open Web Text)

Max Activating Token Index: 374

Text #14

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7100. Min Act: -0.1700

Data Index: 5248922 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7137. Min Act: -0.1700

Data Index: 6406927 (Open Web Text)

Max Activating Token Index: 961

Text #16

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7046. Min Act: -0.1700

Data Index: 1538130 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7062. Min Act: -0.1700

Data Index: 129410 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7002. Min Act: -0.1700

Data Index: 3815231 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 1.7670. Min Range: -1.7670

Max Act: 1.7017. Min Act: -0.1700

Data Index: 5772528 (Open Web Text)

Max Activating Token Index: 520