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

Dataset: Open Web Text

Neuron 1362 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: 1.5726. Min Range: -1.5726

Max Act: 1.5726. Min Act: -0.1700

Data Index: 8066572 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5572. Min Act: -0.1700

Data Index: 848029 (Open Web Text)

Max Activating Token Index: 634

Text #2

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5451. Min Act: -0.1700

Data Index: 1294014 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5395. Min Act: -0.1700

Data Index: 1975177 (Open Web Text)

Max Activating Token Index: 389

Text #4

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5368. Min Act: -0.1700

Data Index: 2013385 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5381. Min Act: -0.1700

Data Index: 7706889 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5205. Min Act: -0.1700

Data Index: 1895731 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5260. Min Act: -0.1700

Data Index: 3550260 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5309. Min Act: -0.1700

Data Index: 6377562 (Open Web Text)

Max Activating Token Index: 751

Text #9

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5137. Min Act: -0.1700

Data Index: 7289799 (Open Web Text)

Max Activating Token Index: 357

Text #10

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5168. Min Act: -0.1700

Data Index: 5071560 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5212. Min Act: -0.1700

Data Index: 5173076 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5107. Min Act: -0.1700

Data Index: 4268884 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5151. Min Act: -0.1700

Data Index: 2783579 (Open Web Text)

Max Activating Token Index: 876

Text #14

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5179. Min Act: -0.1700

Data Index: 1764636 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5145. Min Act: -0.1700

Data Index: 5583589 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5066. Min Act: -0.1700

Data Index: 5319949 (Open Web Text)

Max Activating Token Index: 960

Text #17

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5098. Min Act: -0.1700

Data Index: 4657393 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5170. Min Act: -0.1700

Data Index: 1929782 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5020. Min Act: -0.1697

Data Index: 5554514 (Open Web Text)

Max Activating Token Index: 321