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

Dataset: Open Web Text

Neuron 1554 in Layer 6

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: 3.4038. Min Range: -3.4038

Max Act: 3.3910. Min Act: -0.1700

Data Index: 3570343 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.3639. Min Act: -0.1700

Data Index: 5205834 (Open Web Text)

Max Activating Token Index: 123

Text #2

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.3906. Min Act: -0.1700

Data Index: 2374124 (Open Web Text)

Max Activating Token Index: 634

Text #3

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.3649. Min Act: -0.1700

Data Index: 6342085 (Open Web Text)

Max Activating Token Index: 812

Text #4

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.4038. Min Act: -0.1700

Data Index: 7686389 (Open Web Text)

Max Activating Token Index: 284

Text #5

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.3839. Min Act: -0.1700

Data Index: 5273485 (Open Web Text)

Max Activating Token Index: 385

Text #6

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.3343. Min Act: -0.1700

Data Index: 7055016 (Open Web Text)

Max Activating Token Index: 126

Text #7

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2787. Min Act: -0.1700

Data Index: 4975532 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2635. Min Act: -0.1700

Data Index: 6165307 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2905. Min Act: -0.1700

Data Index: 1830056 (Open Web Text)

Max Activating Token Index: 979

Text #10

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2976. Min Act: -0.1700

Data Index: 2953718 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2830. Min Act: -0.1700

Data Index: 7166716 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2822. Min Act: -0.1700

Data Index: 5900360 (Open Web Text)

Max Activating Token Index: 605

Text #13

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2787. Min Act: -0.1700

Data Index: 8767771 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2772. Min Act: -0.1700

Data Index: 6231290 (Open Web Text)

Max Activating Token Index: 807

Text #15

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2635. Min Act: -0.1700

Data Index: 5215941 (Open Web Text)

Max Activating Token Index: 984

Text #16

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2198. Min Act: -0.1700

Data Index: 3469361 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2427. Min Act: -0.1700

Data Index: 6401724 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.2118. Min Act: -0.1700

Data Index: 99683 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 3.4038. Min Range: -3.4038

Max Act: 3.1915. Min Act: -0.1700

Data Index: 5331644 (Open Web Text)

Max Activating Token Index: 780