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

Dataset: Open Web Text

Neuron 463 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: 3.7869. Min Range: -3.7869

Max Act: 3.7869. Min Act: -0.1700

Data Index: 1555629 (Open Web Text)

Max Activating Token Index: 924

Text #1

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.7260. Min Act: -0.1700

Data Index: 4414901 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.7187. Min Act: -0.1700

Data Index: 6680132 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.7179. Min Act: -0.1700

Data Index: 7419931 (Open Web Text)

Max Activating Token Index: 524

Text #4

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6600. Min Act: -0.1700

Data Index: 1737655 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6704. Min Act: -0.1700

Data Index: 4019162 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6802. Min Act: -0.1700

Data Index: 3435081 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6663. Min Act: -0.1700

Data Index: 6621423 (Open Web Text)

Max Activating Token Index: 54

Text #8

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6836. Min Act: -0.1700

Data Index: 3940462 (Open Web Text)

Max Activating Token Index: 678

Text #9

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6851. Min Act: -0.1700

Data Index: 7081226 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6775. Min Act: -0.1700

Data Index: 44278 (Open Web Text)

Max Activating Token Index: 235

Text #11

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6201. Min Act: -0.1700

Data Index: 5936286 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6391. Min Act: -0.1700

Data Index: 7497588 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6293. Min Act: -0.1700

Data Index: 7386601 (Open Web Text)

Max Activating Token Index: 506

Text #14

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6103. Min Act: -0.1700

Data Index: 972768 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6183. Min Act: -0.1700

Data Index: 5938951 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.5897. Min Act: -0.1700

Data Index: 44260 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6025. Min Act: -0.1700

Data Index: 7398759 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.5802. Min Act: -0.1700

Data Index: 6171595 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.5781. Min Act: -0.1700

Data Index: 4368576 (Open Web Text)

Max Activating Token Index: 27