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

Dataset: Open Web Text

Neuron 2340 in Layer 4

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: 4.7171. Min Range: -4.7171

Max Act: 4.7171. Min Act: -0.1700

Data Index: 5554523 (Open Web Text)

Max Activating Token Index: 478

Text #1

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.7045. Min Act: -0.1700

Data Index: 4124127 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.6021. Min Act: -0.1700

Data Index: 8160465 (Open Web Text)

Max Activating Token Index: 169

Text #3

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5952. Min Act: -0.1700

Data Index: 5806910 (Open Web Text)

Max Activating Token Index: 171

Text #4

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5791. Min Act: -0.1700

Data Index: 1829910 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5458. Min Act: -0.1700

Data Index: 8752682 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.6032. Min Act: -0.1700

Data Index: 8253492 (Open Web Text)

Max Activating Token Index: 472

Text #7

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5752. Min Act: -0.1700

Data Index: 72226 (Open Web Text)

Max Activating Token Index: 323

Text #8

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5460. Min Act: -0.1700

Data Index: 2687487 (Open Web Text)

Max Activating Token Index: 353

Text #9

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5446. Min Act: -0.1700

Data Index: 3100516 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5168. Min Act: -0.1700

Data Index: 5982377 (Open Web Text)

Max Activating Token Index: 791

Text #11

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5265. Min Act: -0.1700

Data Index: 7348882 (Open Web Text)

Max Activating Token Index: 208

Text #12

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5228. Min Act: -0.1700

Data Index: 4667770 (Open Web Text)

Max Activating Token Index: 689

Text #13

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5641. Min Act: -0.1700

Data Index: 108086 (Open Web Text)

Max Activating Token Index: 832

Text #14

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5395. Min Act: -0.1700

Data Index: 111608 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5520. Min Act: -0.1700

Data Index: 478741 (Open Web Text)

Max Activating Token Index: 312

Text #16

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.4995. Min Act: -0.1700

Data Index: 6034723 (Open Web Text)

Max Activating Token Index: 555

Text #17

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.5301. Min Act: -0.1700

Data Index: 6072606 (Open Web Text)

Max Activating Token Index: 323

Text #18

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.4904. Min Act: -0.1700

Data Index: 6337548 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 4.7171. Min Range: -4.7171

Max Act: 4.4782. Min Act: -0.1700

Data Index: 7820191 (Open Web Text)

Max Activating Token Index: 410