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

Dataset: Open Web Text

Neuron 56 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: 4.3882. Min Range: -4.3882

Max Act: 4.3882. Min Act: -0.1700

Data Index: 6744278 (Open Web Text)

Max Activating Token Index: 735

Text #1

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2728. Min Act: -0.1700

Data Index: 6810542 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2662. Min Act: -0.1700

Data Index: 5223523 (Open Web Text)

Max Activating Token Index: 547

Text #3

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2864. Min Act: -0.1700

Data Index: 6550525 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2454. Min Act: -0.1700

Data Index: 1305586 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2185. Min Act: -0.1700

Data Index: 2053792 (Open Web Text)

Max Activating Token Index: 594

Text #6

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2397. Min Act: -0.1700

Data Index: 5589343 (Open Web Text)

Max Activating Token Index: 41

Text #7

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2496. Min Act: -0.1700

Data Index: 3783954 (Open Web Text)

Max Activating Token Index: 878

Text #8

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2466. Min Act: -0.1700

Data Index: 242737 (Open Web Text)

Max Activating Token Index: 193

Text #9

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2057. Min Act: -0.1700

Data Index: 655492 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2057. Min Act: -0.1700

Data Index: 8127561 (Open Web Text)

Max Activating Token Index: 457

Text #11

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2000. Min Act: -0.1700

Data Index: 7590589 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1810. Min Act: -0.1700

Data Index: 1571285 (Open Web Text)

Max Activating Token Index: 820

Text #13

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1700. Min Act: -0.1700

Data Index: 1028529 (Open Web Text)

Max Activating Token Index: 729

Text #14

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1772. Min Act: -0.1700

Data Index: 8229593 (Open Web Text)

Max Activating Token Index: 130

Text #15

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1754. Min Act: -0.1700

Data Index: 7963503 (Open Web Text)

Max Activating Token Index: 132

Text #16

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1622. Min Act: -0.1700

Data Index: 5490852 (Open Web Text)

Max Activating Token Index: 811

Text #17

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1277. Min Act: -0.1700

Data Index: 3922911 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1609. Min Act: -0.1700

Data Index: 800763 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1162. Min Act: -0.1700

Data Index: 6872925 (Open Web Text)

Max Activating Token Index: 534