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

Dataset: Open Web Text

Neuron 1759 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: 1.2874. Min Range: -1.2874

Max Act: 1.2837. Min Act: -0.1700

Data Index: 4703773 (Open Web Text)

Max Activating Token Index: 380

Text #1

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2874. Min Act: -0.1700

Data Index: 8449185 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2690. Min Act: -0.1698

Data Index: 5617407 (Open Web Text)

Max Activating Token Index: 190

Text #3

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2527. Min Act: -0.1700

Data Index: 7873980 (Open Web Text)

Max Activating Token Index: 757

Text #4

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2430. Min Act: -0.1700

Data Index: 7901849 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2208. Min Act: -0.1700

Data Index: 8256020 (Open Web Text)

Max Activating Token Index: 495

Text #6

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2148. Min Act: -0.1697

Data Index: 2578004 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2223. Min Act: -0.1700

Data Index: 4353761 (Open Web Text)

Max Activating Token Index: 73

Text #8

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2072. Min Act: -0.1700

Data Index: 7654715 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2101. Min Act: -0.1700

Data Index: 5713369 (Open Web Text)

Max Activating Token Index: 80

Text #10

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2104. Min Act: -0.1700

Data Index: 8782639 (Open Web Text)

Max Activating Token Index: 361

Text #11

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1993. Min Act: -0.1700

Data Index: 5531826 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1951. Min Act: -0.1700

Data Index: 7646786 (Open Web Text)

Max Activating Token Index: 451

Text #13

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2008. Min Act: -0.1700

Data Index: 3848158 (Open Web Text)

Max Activating Token Index: 1008

Text #14

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1863. Min Act: -0.1698

Data Index: 816731 (Open Web Text)

Max Activating Token Index: 887

Text #15

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1834. Min Act: -0.1700

Data Index: 8035950 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1771. Min Act: -0.1690

Data Index: 2056120 (Open Web Text)

Max Activating Token Index: 422

Text #17

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1539. Min Act: -0.1700

Data Index: 1697747 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1692. Min Act: -0.1700

Data Index: 1942917 (Open Web Text)

Max Activating Token Index: 824

Text #19

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1673. Min Act: -0.1510

Data Index: 6353276 (Open Web Text)

Max Activating Token Index: 638