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

Dataset: Open Web Text

Neuron 2651 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: 3.1623. Min Range: -3.1623

Max Act: 3.1623. Min Act: -0.1700

Data Index: 8217261 (Open Web Text)

Max Activating Token Index: 284

Text #1

Max Range: 3.1623. Min Range: -3.1623

Max Act: 3.1031. Min Act: -0.1700

Data Index: 8624397 (Open Web Text)

Max Activating Token Index: 597

Text #2

Max Range: 3.1623. Min Range: -3.1623

Max Act: 3.0000. Min Act: -0.1700

Data Index: 2161138 (Open Web Text)

Max Activating Token Index: 723

Text #3

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9680. Min Act: -0.1700

Data Index: 813172 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9469. Min Act: -0.1700

Data Index: 4810784 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9526. Min Act: -0.1700

Data Index: 3957683 (Open Web Text)

Max Activating Token Index: 845

Text #6

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9631. Min Act: -0.1700

Data Index: 2638738 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9376. Min Act: -0.1700

Data Index: 7922678 (Open Web Text)

Max Activating Token Index: 297

Text #8

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9494. Min Act: -0.1700

Data Index: 3264871 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9441. Min Act: -0.1700

Data Index: 3409924 (Open Web Text)

Max Activating Token Index: 885

Text #10

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9092. Min Act: -0.1700

Data Index: 353666 (Open Web Text)

Max Activating Token Index: 564

Text #11

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9269. Min Act: -0.1700

Data Index: 1473788 (Open Web Text)

Max Activating Token Index: 670

Text #12

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9051. Min Act: -0.1700

Data Index: 1709854 (Open Web Text)

Max Activating Token Index: 641

Text #13

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9273. Min Act: -0.1700

Data Index: 7577482 (Open Web Text)

Max Activating Token Index: 603

Text #14

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9326. Min Act: -0.1700

Data Index: 2238254 (Open Web Text)

Max Activating Token Index: 838

Text #15

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9060. Min Act: -0.1700

Data Index: 941773 (Open Web Text)

Max Activating Token Index: 547

Text #16

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.8880. Min Act: -0.1700

Data Index: 2862544 (Open Web Text)

Max Activating Token Index: 219

Text #17

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.8740. Min Act: -0.1700

Data Index: 5785875 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.8687. Min Act: -0.1700

Data Index: 3711235 (Open Web Text)

Max Activating Token Index: 762

Text #19

Max Range: 3.1623. Min Range: -3.1623

Max Act: 2.9080. Min Act: -0.1700

Data Index: 3967241 (Open Web Text)

Max Activating Token Index: 695