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

Dataset: Open Web Text

Neuron 1986 in Layer 4

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: 3.9640. Min Range: -3.9640

Max Act: 3.9640. Min Act: -0.1700

Data Index: 186894 (Open Web Text)

Max Activating Token Index: 135

Text #1

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.7788. Min Act: -0.1700

Data Index: 672771 (Open Web Text)

Max Activating Token Index: 787

Text #2

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.6597. Min Act: -0.1700

Data Index: 7003472 (Open Web Text)

Max Activating Token Index: 506

Text #3

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.6918. Min Act: -0.1700

Data Index: 8067151 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.6240. Min Act: -0.1700

Data Index: 2968745 (Open Web Text)

Max Activating Token Index: 261

Text #5

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.6061. Min Act: -0.1700

Data Index: 2045455 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.5474. Min Act: -0.1700

Data Index: 232398 (Open Web Text)

Max Activating Token Index: 582

Text #7

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.5946. Min Act: -0.1700

Data Index: 2172859 (Open Web Text)

Max Activating Token Index: 830

Text #8

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.5608. Min Act: -0.1700

Data Index: 2656778 (Open Web Text)

Max Activating Token Index: 963

Text #9

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.5176. Min Act: -0.1700

Data Index: 1464665 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.5151. Min Act: -0.1700

Data Index: 2042505 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4796. Min Act: -0.1700

Data Index: 1028416 (Open Web Text)

Max Activating Token Index: 803

Text #12

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4676. Min Act: -0.1700

Data Index: 3259881 (Open Web Text)

Max Activating Token Index: 921

Text #13

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4823. Min Act: -0.1700

Data Index: 7199185 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4452. Min Act: -0.1700

Data Index: 4074816 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4629. Min Act: -0.1700

Data Index: 8247431 (Open Web Text)

Max Activating Token Index: 821

Text #16

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4692. Min Act: -0.1700

Data Index: 2009166 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.3904. Min Act: -0.1700

Data Index: 2358475 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4230. Min Act: -0.1700

Data Index: 4027060 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4133. Min Act: -0.1700

Data Index: 7125652 (Open Web Text)

Max Activating Token Index: 352