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

Dataset: Open Web Text

Neuron 2321 in Layer 3

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: 3.6590. Min Range: -3.6590

Max Act: 3.6590. Min Act: -0.1700

Data Index: 653995 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.4222. Min Act: -0.1700

Data Index: 6709 (Open Web Text)

Max Activating Token Index: 116

Text #2

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.3649. Min Act: -0.1700

Data Index: 913166 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.3534. Min Act: -0.1700

Data Index: 7685355 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.3351. Min Act: -0.1700

Data Index: 4379383 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.3171. Min Act: -0.1700

Data Index: 5736729 (Open Web Text)

Max Activating Token Index: 998

Text #6

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.3248. Min Act: -0.1700

Data Index: 3626549 (Open Web Text)

Max Activating Token Index: 961

Text #7

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.3051. Min Act: -0.1700

Data Index: 4431561 (Open Web Text)

Max Activating Token Index: 941

Text #8

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.3133. Min Act: -0.1700

Data Index: 2125334 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2984. Min Act: -0.1700

Data Index: 8728075 (Open Web Text)

Max Activating Token Index: 818

Text #10

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2753. Min Act: -0.1700

Data Index: 4907764 (Open Web Text)

Max Activating Token Index: 650

Text #11

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2597. Min Act: -0.1700

Data Index: 812064 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2714. Min Act: -0.1700

Data Index: 64302 (Open Web Text)

Max Activating Token Index: 803

Text #13

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2531. Min Act: -0.1700

Data Index: 7374462 (Open Web Text)

Max Activating Token Index: 691

Text #14

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2775. Min Act: -0.1700

Data Index: 7264830 (Open Web Text)

Max Activating Token Index: 375

Text #15

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2531. Min Act: -0.1700

Data Index: 4391792 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2600. Min Act: -0.1700

Data Index: 2408080 (Open Web Text)

Max Activating Token Index: 369

Text #17

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2616. Min Act: -0.1700

Data Index: 1925977 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2427. Min Act: -0.1700

Data Index: 2675204 (Open Web Text)

Max Activating Token Index: 86

Text #19

Max Range: 3.6590. Min Range: -3.6590

Max Act: 3.2623. Min Act: -0.1700

Data Index: 4748110 (Open Web Text)

Max Activating Token Index: 376