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

Dataset: Open Web Text

Neuron 321 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: 1.9425. Min Range: -1.9425

Max Act: 1.9425. Min Act: -0.1700

Data Index: 3265097 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.9425. Min Act: -0.1700

Data Index: 8533443 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.9190. Min Act: -0.1700

Data Index: 6361674 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.9153. Min Act: -0.1698

Data Index: 1802573 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8637. Min Act: -0.1700

Data Index: 4878504 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8615. Min Act: -0.1700

Data Index: 7481686 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8567. Min Act: -0.1700

Data Index: 687535 (Open Web Text)

Max Activating Token Index: 588

Text #7

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8419. Min Act: -0.1647

Data Index: 5787140 (Open Web Text)

Max Activating Token Index: 286

Text #8

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8201. Min Act: -0.1700

Data Index: 5007968 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8235. Min Act: -0.1700

Data Index: 2748348 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8020. Min Act: -0.1700

Data Index: 6900898 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8172. Min Act: -0.1684

Data Index: 6069884 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.8045. Min Act: -0.1700

Data Index: 8522059 (Open Web Text)

Max Activating Token Index: 54

Text #13

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.7912. Min Act: -0.1700

Data Index: 5003433 (Open Web Text)

Max Activating Token Index: 620

Text #14

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.7859. Min Act: -0.1700

Data Index: 1417977 (Open Web Text)

Max Activating Token Index: 56

Text #15

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.7840. Min Act: -0.1652

Data Index: 6140872 (Open Web Text)

Max Activating Token Index: 69

Text #16

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.7703. Min Act: -0.1700

Data Index: 4941681 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.7812. Min Act: -0.1700

Data Index: 2676775 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.7696. Min Act: -0.1700

Data Index: 3834010 (Open Web Text)

Max Activating Token Index: 82

Text #19

Max Range: 1.9425. Min Range: -1.9425

Max Act: 1.7759. Min Act: -0.1700

Data Index: 6625797 (Open Web Text)

Max Activating Token Index: 700