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

Dataset: Open Web Text

Neuron 434 in Layer 6

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: 4.3509. Min Range: -4.3509

Max Act: 4.3509. Min Act: -0.1700

Data Index: 1046845 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.2653. Min Act: -0.1700

Data Index: 4125645 (Open Web Text)

Max Activating Token Index: 165

Text #2

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.1872. Min Act: -0.1700

Data Index: 1778321 (Open Web Text)

Max Activating Token Index: 768

Text #3

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.1512. Min Act: -0.1700

Data Index: 8101599 (Open Web Text)

Max Activating Token Index: 837

Text #4

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.1675. Min Act: -0.1700

Data Index: 8283866 (Open Web Text)

Max Activating Token Index: 654

Text #5

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.1685. Min Act: -0.1700

Data Index: 8681924 (Open Web Text)

Max Activating Token Index: 93

Text #6

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.1546. Min Act: -0.1700

Data Index: 1497502 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.1168. Min Act: -0.1700

Data Index: 8121503 (Open Web Text)

Max Activating Token Index: 777

Text #8

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.1396. Min Act: -0.1700

Data Index: 3932333 (Open Web Text)

Max Activating Token Index: 360

Text #9

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0970. Min Act: -0.1700

Data Index: 6422342 (Open Web Text)

Max Activating Token Index: 676

Text #10

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0836. Min Act: -0.1700

Data Index: 3648862 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0867. Min Act: -0.1700

Data Index: 4453827 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0927. Min Act: -0.1700

Data Index: 8089008 (Open Web Text)

Max Activating Token Index: 208

Text #13

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0450. Min Act: -0.1700

Data Index: 986875 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0453. Min Act: -0.1700

Data Index: 6558235 (Open Web Text)

Max Activating Token Index: 725

Text #15

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0494. Min Act: -0.1700

Data Index: 7335191 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0370. Min Act: -0.1700

Data Index: 486883 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0640. Min Act: -0.1700

Data Index: 2665848 (Open Web Text)

Max Activating Token Index: 127

Text #18

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.9956. Min Act: -0.1700

Data Index: 5095501 (Open Web Text)

Max Activating Token Index: 848

Text #19

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.0194. Min Act: -0.1700

Data Index: 3140126 (Open Web Text)

Max Activating Token Index: 970