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

Dataset: Open Web Text

Neuron 5 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: 1.9145. Min Range: -1.9145

Max Act: 1.8998. Min Act: -0.1700

Data Index: 4985591 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.9072. Min Act: -0.1700

Data Index: 5255674 (Open Web Text)

Max Activating Token Index: 238

Text #2

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.9019. Min Act: -0.1700

Data Index: 4938594 (Open Web Text)

Max Activating Token Index: 127

Text #3

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8962. Min Act: -0.1700

Data Index: 7479539 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.9145. Min Act: -0.1700

Data Index: 1055663 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8927. Min Act: -0.1700

Data Index: 3658288 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.9013. Min Act: -0.1700

Data Index: 583245 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8734. Min Act: -0.1700

Data Index: 7339459 (Open Web Text)

Max Activating Token Index: 91

Text #8

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8747. Min Act: -0.1700

Data Index: 8294696 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8647. Min Act: -0.1700

Data Index: 7438867 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8763. Min Act: -0.1700

Data Index: 604709 (Open Web Text)

Max Activating Token Index: 537

Text #11

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8686. Min Act: -0.1700

Data Index: 5923988 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8668. Min Act: -0.1700

Data Index: 5313079 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8464. Min Act: -0.1700

Data Index: 722860 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8561. Min Act: -0.1700

Data Index: 1356654 (Open Web Text)

Max Activating Token Index: 458

Text #15

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8556. Min Act: -0.1700

Data Index: 2326883 (Open Web Text)

Max Activating Token Index: 528

Text #16

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8515. Min Act: -0.1700

Data Index: 4465040 (Open Web Text)

Max Activating Token Index: 179

Text #17

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8510. Min Act: -0.1700

Data Index: 5481565 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8427. Min Act: -0.1700

Data Index: 7995162 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 1.9145. Min Range: -1.9145

Max Act: 1.8533. Min Act: -0.1700

Data Index: 1543546 (Open Web Text)

Max Activating Token Index: 156