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

Dataset: Open Web Text

Neuron 1191 in Layer 2

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: 4.4559. Min Range: -4.4559

Max Act: 4.4559. Min Act: -0.1700

Data Index: 5698669 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.3630. Min Act: -0.1700

Data Index: 5778208 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.3020. Min Act: -0.1700

Data Index: 1867873 (Open Web Text)

Max Activating Token Index: 696

Text #3

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.2739. Min Act: -0.1700

Data Index: 2718430 (Open Web Text)

Max Activating Token Index: 841

Text #4

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.2593. Min Act: -0.1700

Data Index: 437976 (Open Web Text)

Max Activating Token Index: 743

Text #5

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.2762. Min Act: -0.1700

Data Index: 3090851 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.2840. Min Act: -0.1700

Data Index: 1999513 (Open Web Text)

Max Activating Token Index: 632

Text #7

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.2324. Min Act: -0.1700

Data Index: 161741 (Open Web Text)

Max Activating Token Index: 943

Text #8

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.2022. Min Act: -0.1700

Data Index: 1822946 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1877. Min Act: -0.1700

Data Index: 6823090 (Open Web Text)

Max Activating Token Index: 731

Text #10

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1929. Min Act: -0.1700

Data Index: 5406966 (Open Web Text)

Max Activating Token Index: 194

Text #11

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1972. Min Act: -0.1700

Data Index: 7954259 (Open Web Text)

Max Activating Token Index: 306

Text #12

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1572. Min Act: -0.1700

Data Index: 890367 (Open Web Text)

Max Activating Token Index: 373

Text #13

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1878. Min Act: -0.1700

Data Index: 927884 (Open Web Text)

Max Activating Token Index: 935

Text #14

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1684. Min Act: -0.1700

Data Index: 2496565 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1910. Min Act: -0.1700

Data Index: 5800228 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1839. Min Act: -0.1700

Data Index: 4910149 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1446. Min Act: -0.1700

Data Index: 5683720 (Open Web Text)

Max Activating Token Index: 699

Text #18

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1419. Min Act: -0.1700

Data Index: 3291182 (Open Web Text)

Max Activating Token Index: 473

Text #19

Max Range: 4.4559. Min Range: -4.4559

Max Act: 4.1477. Min Act: -0.1700

Data Index: 4686550 (Open Web Text)

Max Activating Token Index: 915