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

Dataset: Open Web Text

Neuron 1453 in Layer 2

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: 1.8987. Min Range: -1.8987

Max Act: 1.8963. Min Act: -0.1700

Data Index: 2127204 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8987. Min Act: -0.1700

Data Index: 3397650 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8769. Min Act: -0.1700

Data Index: 3483245 (Open Web Text)

Max Activating Token Index: 587

Text #3

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8718. Min Act: -0.1700

Data Index: 752965 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8704. Min Act: -0.1700

Data Index: 1716189 (Open Web Text)

Max Activating Token Index: 853

Text #5

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8659. Min Act: -0.1700

Data Index: 5653498 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8603. Min Act: -0.1700

Data Index: 7399882 (Open Web Text)

Max Activating Token Index: 959

Text #7

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8609. Min Act: -0.1700

Data Index: 3541417 (Open Web Text)

Max Activating Token Index: 277

Text #8

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8570. Min Act: -0.1700

Data Index: 3490441 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8499. Min Act: -0.1700

Data Index: 6800323 (Open Web Text)

Max Activating Token Index: 45

Text #10

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8541. Min Act: -0.1700

Data Index: 8185622 (Open Web Text)

Max Activating Token Index: 76

Text #11

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8544. Min Act: -0.1700

Data Index: 6304542 (Open Web Text)

Max Activating Token Index: 349

Text #12

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8500. Min Act: -0.1700

Data Index: 1117816 (Open Web Text)

Max Activating Token Index: 393

Text #13

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8490. Min Act: -0.1700

Data Index: 5098417 (Open Web Text)

Max Activating Token Index: 782

Text #14

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8331. Min Act: -0.1700

Data Index: 5360107 (Open Web Text)

Max Activating Token Index: 106

Text #15

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8373. Min Act: -0.1700

Data Index: 1704864 (Open Web Text)

Max Activating Token Index: 761

Text #16

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8414. Min Act: -0.1700

Data Index: 1585682 (Open Web Text)

Max Activating Token Index: 263

Text #17

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8257. Min Act: -0.1700

Data Index: 6647236 (Open Web Text)

Max Activating Token Index: 316

Text #18

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8366. Min Act: -0.1700

Data Index: 3537869 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8197. Min Act: -0.1700

Data Index: 5849184 (Open Web Text)

Max Activating Token Index: 952