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

Dataset: Open Web Text

Neuron 2373 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: 1.8691. Min Range: -1.8691

Max Act: 1.8691. Min Act: -0.1700

Data Index: 6266485 (Open Web Text)

Max Activating Token Index: 748

Text #1

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8605. Min Act: -0.1700

Data Index: 7580756 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8655. Min Act: -0.1700

Data Index: 4746069 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8586. Min Act: -0.1700

Data Index: 239646 (Open Web Text)

Max Activating Token Index: 137

Text #4

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8546. Min Act: -0.1700

Data Index: 7541094 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8552. Min Act: -0.1700

Data Index: 413907 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8362. Min Act: -0.1700

Data Index: 4446902 (Open Web Text)

Max Activating Token Index: 219

Text #7

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8200. Min Act: -0.1700

Data Index: 7823264 (Open Web Text)

Max Activating Token Index: 691

Text #8

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8229. Min Act: -0.1700

Data Index: 6142596 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8056. Min Act: -0.1700

Data Index: 7729226 (Open Web Text)

Max Activating Token Index: 361

Text #10

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8089. Min Act: -0.1700

Data Index: 5131012 (Open Web Text)

Max Activating Token Index: 362

Text #11

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8112. Min Act: -0.1700

Data Index: 4857816 (Open Web Text)

Max Activating Token Index: 198

Text #12

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8000. Min Act: -0.1700

Data Index: 1212577 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7955. Min Act: -0.1698

Data Index: 2212478 (Open Web Text)

Max Activating Token Index: 734

Text #14

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7911. Min Act: -0.1700

Data Index: 8659913 (Open Web Text)

Max Activating Token Index: 149

Text #15

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7938. Min Act: -0.1700

Data Index: 6629596 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7877. Min Act: -0.1700

Data Index: 5737866 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7909. Min Act: -0.1699

Data Index: 778143 (Open Web Text)

Max Activating Token Index: 772

Text #18

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7934. Min Act: -0.1700

Data Index: 8411544 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7978. Min Act: -0.1700

Data Index: 4135618 (Open Web Text)

Max Activating Token Index: 889