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

Dataset: Open Web Text

Neuron 2678 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: 3.3890. Min Range: -3.3890

Max Act: 3.3890. Min Act: -0.1700

Data Index: 3931875 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3631. Min Act: -0.1700

Data Index: 1766854 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3511. Min Act: -0.1700

Data Index: 2962097 (Open Web Text)

Max Activating Token Index: 967

Text #3

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3115. Min Act: -0.1700

Data Index: 5701663 (Open Web Text)

Max Activating Token Index: 946

Text #4

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3170. Min Act: -0.1700

Data Index: 7075968 (Open Web Text)

Max Activating Token Index: 872

Text #5

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2908. Min Act: -0.1700

Data Index: 7885887 (Open Web Text)

Max Activating Token Index: 997

Text #6

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3075. Min Act: -0.1700

Data Index: 5893804 (Open Web Text)

Max Activating Token Index: 941

Text #7

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3150. Min Act: -0.1700

Data Index: 7734615 (Open Web Text)

Max Activating Token Index: 488

Text #8

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2956. Min Act: -0.1700

Data Index: 6084470 (Open Web Text)

Max Activating Token Index: 981

Text #9

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2469. Min Act: -0.1700

Data Index: 613798 (Open Web Text)

Max Activating Token Index: 592

Text #10

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2652. Min Act: -0.1700

Data Index: 788328 (Open Web Text)

Max Activating Token Index: 323

Text #11

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2676. Min Act: -0.1700

Data Index: 4276032 (Open Web Text)

Max Activating Token Index: 504

Text #12

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2481. Min Act: -0.1700

Data Index: 4864672 (Open Web Text)

Max Activating Token Index: 329

Text #13

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2016. Min Act: -0.1700

Data Index: 6170263 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2288. Min Act: -0.1700

Data Index: 8349511 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2239. Min Act: -0.1700

Data Index: 8074900 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2116. Min Act: -0.1700

Data Index: 2961003 (Open Web Text)

Max Activating Token Index: 1002

Text #17

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2123. Min Act: -0.1700

Data Index: 4790215 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2178. Min Act: -0.1700

Data Index: 7131251 (Open Web Text)

Max Activating Token Index: 690

Text #19

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.1767. Min Act: -0.1700

Data Index: 4814884 (Open Web Text)

Max Activating Token Index: 627