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

Dataset: Open Web Text

Neuron 1583 in Layer 1

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: 0.8338. Min Range: -0.8338

Max Act: 0.8338. Min Act: -0.1700

Data Index: 6105088 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7999. Min Act: -0.1700

Data Index: 940304 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7865. Min Act: -0.1700

Data Index: 8176446 (Open Web Text)

Max Activating Token Index: 599

Text #3

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7778. Min Act: -0.1700

Data Index: 8815990 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7788. Min Act: -0.1700

Data Index: 7862537 (Open Web Text)

Max Activating Token Index: 590

Text #5

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7777. Min Act: -0.1700

Data Index: 2757423 (Open Web Text)

Max Activating Token Index: 606

Text #6

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7641. Min Act: -0.1700

Data Index: 4722106 (Open Web Text)

Max Activating Token Index: 621

Text #7

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7628. Min Act: -0.1700

Data Index: 1773763 (Open Web Text)

Max Activating Token Index: 618

Text #8

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7643. Min Act: -0.1700

Data Index: 1163637 (Open Web Text)

Max Activating Token Index: 622

Text #9

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7552. Min Act: -0.1700

Data Index: 3654071 (Open Web Text)

Max Activating Token Index: 623

Text #10

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7635. Min Act: -0.1700

Data Index: 7887063 (Open Web Text)

Max Activating Token Index: 597

Text #11

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7578. Min Act: -0.1700

Data Index: 6908555 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7560. Min Act: -0.1700

Data Index: 611113 (Open Web Text)

Max Activating Token Index: 600

Text #13

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7519. Min Act: -0.1700

Data Index: 7987197 (Open Web Text)

Max Activating Token Index: 612

Text #14

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7508. Min Act: -0.1700

Data Index: 2500700 (Open Web Text)

Max Activating Token Index: 600

Text #15

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7406. Min Act: -0.1700

Data Index: 1268810 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7469. Min Act: -0.1700

Data Index: 8249089 (Open Web Text)

Max Activating Token Index: 633

Text #17

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7439. Min Act: -0.1700

Data Index: 6851921 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7368. Min Act: -0.1700

Data Index: 7656629 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7418. Min Act: -0.1700

Data Index: 3405194 (Open Web Text)

Max Activating Token Index: 602