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

Dataset: Open Web Text

Neuron 561 in Layer 0

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: 2.5512. Min Range: -2.5512

Max Act: 2.5512. Min Act: -0.1700

Data Index: 8589274 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5342. Min Act: -0.1700

Data Index: 4948712 (Open Web Text)

Max Activating Token Index: 701

Text #2

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5504. Min Act: -0.1700

Data Index: 2816454 (Open Web Text)

Max Activating Token Index: 654

Text #3

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5272. Min Act: -0.1700

Data Index: 2524810 (Open Web Text)

Max Activating Token Index: 504

Text #4

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5231. Min Act: -0.1700

Data Index: 8400647 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5225. Min Act: -0.1700

Data Index: 4288779 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5076. Min Act: -0.1700

Data Index: 6764248 (Open Web Text)

Max Activating Token Index: 808

Text #7

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5016. Min Act: -0.1700

Data Index: 2752615 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5015. Min Act: -0.1700

Data Index: 2203711 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5016. Min Act: -0.1700

Data Index: 607025 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.5016. Min Act: -0.1700

Data Index: 1473469 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4977. Min Act: -0.1700

Data Index: 6827481 (Open Web Text)

Max Activating Token Index: 102

Text #12

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4897. Min Act: -0.1700

Data Index: 1404954 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4828. Min Act: -0.1700

Data Index: 7299227 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4850. Min Act: -0.1700

Data Index: 6752757 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4829. Min Act: -0.1700

Data Index: 584370 (Open Web Text)

Max Activating Token Index: 504

Text #16

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4930. Min Act: -0.1700

Data Index: 5131003 (Open Web Text)

Max Activating Token Index: 331

Text #17

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4832. Min Act: -0.1700

Data Index: 2186153 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4788. Min Act: -0.1700

Data Index: 864 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 2.5512. Min Range: -2.5512

Max Act: 2.4640. Min Act: -0.1700

Data Index: 2949072 (Open Web Text)

Max Activating Token Index: 3