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

Dataset: Open Web Text

Neuron 1836 in Layer 0

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: 4.0362. Min Range: -4.0362

Max Act: 4.0362. Min Act: -0.1700

Data Index: 4129365 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.0362. Min Range: -4.0362

Max Act: 4.0229. Min Act: -0.1700

Data Index: 4049942 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9955. Min Act: -0.1700

Data Index: 5156903 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9504. Min Act: -0.1700

Data Index: 3456516 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9476. Min Act: -0.1700

Data Index: 3830566 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9294. Min Act: -0.1700

Data Index: 1005665 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9352. Min Act: -0.1700

Data Index: 2332525 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9162. Min Act: -0.1700

Data Index: 3378592 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9290. Min Act: -0.1700

Data Index: 4057784 (Open Web Text)

Max Activating Token Index: 59

Text #9

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9010. Min Act: -0.1700

Data Index: 2869612 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8854. Min Act: -0.1700

Data Index: 972704 (Open Web Text)

Max Activating Token Index: 46

Text #11

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8881. Min Act: -0.1700

Data Index: 1589117 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8783. Min Act: -0.1700

Data Index: 6579269 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8547. Min Act: -0.1700

Data Index: 7033875 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8468. Min Act: -0.1700

Data Index: 7960818 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8240. Min Act: -0.1700

Data Index: 1074972 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8294. Min Act: -0.1700

Data Index: 7184015 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8416. Min Act: -0.1700

Data Index: 7480290 (Open Web Text)

Max Activating Token Index: 291

Text #18

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.8327. Min Act: -0.1700

Data Index: 6194417 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.7923. Min Act: -0.1700

Data Index: 1720633 (Open Web Text)

Max Activating Token Index: 918