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

Dataset: Open Web Text

Neuron 1229 in Layer 3

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: 4.3654. Min Range: -4.3654

Max Act: 4.3654. Min Act: -0.1700

Data Index: 977797 (Open Web Text)

Max Activating Token Index: 82

Text #1

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.2566. Min Act: -0.1700

Data Index: 7816349 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1440. Min Act: -0.1700

Data Index: 5850484 (Open Web Text)

Max Activating Token Index: 926

Text #3

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0956. Min Act: -0.1700

Data Index: 6075854 (Open Web Text)

Max Activating Token Index: 950

Text #4

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1173. Min Act: -0.1700

Data Index: 6378316 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1297. Min Act: -0.1700

Data Index: 4389150 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0938. Min Act: -0.1700

Data Index: 1933246 (Open Web Text)

Max Activating Token Index: 458

Text #7

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1207. Min Act: -0.1700

Data Index: 2991267 (Open Web Text)

Max Activating Token Index: 208

Text #8

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0854. Min Act: -0.1700

Data Index: 5266669 (Open Web Text)

Max Activating Token Index: 269

Text #9

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0755. Min Act: -0.1700

Data Index: 5849733 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0514. Min Act: -0.1700

Data Index: 6143953 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0313. Min Act: -0.1700

Data Index: 8270893 (Open Web Text)

Max Activating Token Index: 605

Text #12

Max Range: 4.3654. Min Range: -4.3654

Max Act: 3.9893. Min Act: -0.1700

Data Index: 1739844 (Open Web Text)

Max Activating Token Index: 417

Text #13

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0071. Min Act: -0.1700

Data Index: 8080565 (Open Web Text)

Max Activating Token Index: 72

Text #14

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0104. Min Act: -0.1700

Data Index: 5136956 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.0124. Min Act: -0.1700

Data Index: 2121005 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 4.3654. Min Range: -4.3654

Max Act: 3.9880. Min Act: -0.1700

Data Index: 252565 (Open Web Text)

Max Activating Token Index: 786

Text #17

Max Range: 4.3654. Min Range: -4.3654

Max Act: 3.9990. Min Act: -0.1700

Data Index: 3541344 (Open Web Text)

Max Activating Token Index: 331

Text #18

Max Range: 4.3654. Min Range: -4.3654

Max Act: 3.9517. Min Act: -0.1700

Data Index: 7677957 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 4.3654. Min Range: -4.3654

Max Act: 3.9669. Min Act: -0.1700

Data Index: 799899 (Open Web Text)

Max Activating Token Index: 567