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

Dataset: Open Web Text

Neuron 2305 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: 3.8284. Min Range: -3.8284

Max Act: 3.8284. Min Act: -0.1700

Data Index: 5188508 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.8094. Min Act: -0.1700

Data Index: 7169854 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.7044. Min Act: -0.1700

Data Index: 4437273 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.7606. Min Act: -0.1700

Data Index: 1637898 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.7273. Min Act: -0.1700

Data Index: 3318611 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.7025. Min Act: -0.1700

Data Index: 2673051 (Open Web Text)

Max Activating Token Index: 513

Text #6

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6868. Min Act: -0.1700

Data Index: 3973795 (Open Web Text)

Max Activating Token Index: 951

Text #7

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.7211. Min Act: -0.1700

Data Index: 4166207 (Open Web Text)

Max Activating Token Index: 425

Text #8

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.7072. Min Act: -0.1700

Data Index: 1347301 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.7013. Min Act: -0.1700

Data Index: 8251875 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6566. Min Act: -0.1700

Data Index: 1136820 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6702. Min Act: -0.1700

Data Index: 1146776 (Open Web Text)

Max Activating Token Index: 743

Text #12

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6595. Min Act: -0.1700

Data Index: 7120456 (Open Web Text)

Max Activating Token Index: 516

Text #13

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6524. Min Act: -0.1700

Data Index: 1698427 (Open Web Text)

Max Activating Token Index: 667

Text #14

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6743. Min Act: -0.1700

Data Index: 5517508 (Open Web Text)

Max Activating Token Index: 215

Text #15

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6519. Min Act: -0.1700

Data Index: 8540612 (Open Web Text)

Max Activating Token Index: 352

Text #16

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6149. Min Act: -0.1700

Data Index: 4958803 (Open Web Text)

Max Activating Token Index: 878

Text #17

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6430. Min Act: -0.1700

Data Index: 4698001 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6429. Min Act: -0.1700

Data Index: 6122666 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 3.8284. Min Range: -3.8284

Max Act: 3.6287. Min Act: -0.1700

Data Index: 4147759 (Open Web Text)

Max Activating Token Index: 708