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

Dataset: Open Web Text

Neuron 2616 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: 3.2267. Min Range: -3.2267

Max Act: 3.2267. Min Act: -0.1700

Data Index: 4031891 (Open Web Text)

Max Activating Token Index: 221

Text #1

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.1575. Min Act: -0.1700

Data Index: 78531 (Open Web Text)

Max Activating Token Index: 613

Text #2

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.1623. Min Act: -0.1700

Data Index: 4057197 (Open Web Text)

Max Activating Token Index: 744

Text #3

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0799. Min Act: -0.1700

Data Index: 6208114 (Open Web Text)

Max Activating Token Index: 227

Text #4

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0539. Min Act: -0.1700

Data Index: 2220254 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0152. Min Act: -0.1700

Data Index: 5639444 (Open Web Text)

Max Activating Token Index: 545

Text #6

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0219. Min Act: -0.1700

Data Index: 1713845 (Open Web Text)

Max Activating Token Index: 599

Text #7

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0059. Min Act: -0.1700

Data Index: 762545 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0079. Min Act: -0.1700

Data Index: 1198929 (Open Web Text)

Max Activating Token Index: 394

Text #9

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9962. Min Act: -0.1700

Data Index: 3963073 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0258. Min Act: -0.1700

Data Index: 6435490 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9830. Min Act: -0.1700

Data Index: 1399686 (Open Web Text)

Max Activating Token Index: 958

Text #12

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0094. Min Act: -0.1700

Data Index: 4110111 (Open Web Text)

Max Activating Token Index: 128

Text #13

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9815. Min Act: -0.1700

Data Index: 971421 (Open Web Text)

Max Activating Token Index: 209

Text #14

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9987. Min Act: -0.1700

Data Index: 8140798 (Open Web Text)

Max Activating Token Index: 346

Text #15

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9974. Min Act: -0.1700

Data Index: 1818822 (Open Web Text)

Max Activating Token Index: 451

Text #16

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9802. Min Act: -0.1700

Data Index: 4743720 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9782. Min Act: -0.1700

Data Index: 5221465 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9688. Min Act: -0.1700

Data Index: 5265229 (Open Web Text)

Max Activating Token Index: 172

Text #19

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9829. Min Act: -0.1700

Data Index: 4636936 (Open Web Text)

Max Activating Token Index: 755