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

Dataset: Open Web Text

Neuron 2348 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: 3.2750. Min Range: -3.2750

Max Act: 3.2750. Min Act: -0.1700

Data Index: 98247 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.2103. Min Act: -0.1700

Data Index: 2329606 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.1581. Min Act: -0.1700

Data Index: 2053040 (Open Web Text)

Max Activating Token Index: 999

Text #3

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.1235. Min Act: -0.1700

Data Index: 7427291 (Open Web Text)

Max Activating Token Index: 182

Text #4

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.1012. Min Act: -0.1700

Data Index: 2331523 (Open Web Text)

Max Activating Token Index: 869

Text #5

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0638. Min Act: -0.1700

Data Index: 7373628 (Open Web Text)

Max Activating Token Index: 765

Text #6

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0471. Min Act: -0.1700

Data Index: 5823979 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0566. Min Act: -0.1700

Data Index: 3099232 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0214. Min Act: -0.1700

Data Index: 8072440 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0004. Min Act: -0.1700

Data Index: 8168557 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0016. Min Act: -0.1700

Data Index: 3132375 (Open Web Text)

Max Activating Token Index: 261

Text #11

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9631. Min Act: -0.1700

Data Index: 717471 (Open Web Text)

Max Activating Token Index: 133

Text #12

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9822. Min Act: -0.1700

Data Index: 5317894 (Open Web Text)

Max Activating Token Index: 879

Text #13

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9666. Min Act: -0.1700

Data Index: 6699008 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9416. Min Act: -0.1700

Data Index: 2187228 (Open Web Text)

Max Activating Token Index: 605

Text #15

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9641. Min Act: -0.1700

Data Index: 8782913 (Open Web Text)

Max Activating Token Index: 28

Text #16

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9191. Min Act: -0.1700

Data Index: 2262820 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9262. Min Act: -0.1700

Data Index: 5134123 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.8919. Min Act: -0.1700

Data Index: 4719163 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.8988. Min Act: -0.1700

Data Index: 6572065 (Open Web Text)

Max Activating Token Index: 246