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

Dataset: Open Web Text

Neuron 3026 in Layer 5

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: 4.2623. Min Range: -4.2623

Max Act: 4.2623. Min Act: -0.1700

Data Index: 87579 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.2269. Min Act: -0.1700

Data Index: 732325 (Open Web Text)

Max Activating Token Index: 801

Text #2

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.2294. Min Act: -0.1700

Data Index: 2776741 (Open Web Text)

Max Activating Token Index: 977

Text #3

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1510. Min Act: -0.1700

Data Index: 3645266 (Open Web Text)

Max Activating Token Index: 59

Text #4

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1257. Min Act: -0.1700

Data Index: 3645265 (Open Web Text)

Max Activating Token Index: 1007

Text #5

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1314. Min Act: -0.1700

Data Index: 326438 (Open Web Text)

Max Activating Token Index: 796

Text #6

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1099. Min Act: -0.1700

Data Index: 6371821 (Open Web Text)

Max Activating Token Index: 959

Text #7

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0853. Min Act: -0.1700

Data Index: 8163638 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0825. Min Act: -0.1700

Data Index: 273404 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0823. Min Act: -0.1700

Data Index: 7555029 (Open Web Text)

Max Activating Token Index: 655

Text #10

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1106. Min Act: -0.1700

Data Index: 4457269 (Open Web Text)

Max Activating Token Index: 841

Text #11

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0823. Min Act: -0.1700

Data Index: 4270299 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0840. Min Act: -0.1700

Data Index: 8521403 (Open Web Text)

Max Activating Token Index: 105

Text #13

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0810. Min Act: -0.1700

Data Index: 8521391 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0726. Min Act: -0.1700

Data Index: 4033571 (Open Web Text)

Max Activating Token Index: 854

Text #15

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0989. Min Act: -0.1700

Data Index: 8261671 (Open Web Text)

Max Activating Token Index: 361

Text #16

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0522. Min Act: -0.1700

Data Index: 1109851 (Open Web Text)

Max Activating Token Index: 922

Text #17

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0200. Min Act: -0.1700

Data Index: 5757725 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0562. Min Act: -0.1700

Data Index: 2015323 (Open Web Text)

Max Activating Token Index: 789

Text #19

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0210. Min Act: -0.1700

Data Index: 5486873 (Open Web Text)

Max Activating Token Index: 603