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

Dataset: Open Web Text

Neuron 677 in Layer 3

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: 4.3773. Min Range: -4.3773

Max Act: 4.3773. Min Act: -0.1700

Data Index: 7397180 (Open Web Text)

Max Activating Token Index: 911

Text #1

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.3299. Min Act: -0.1700

Data Index: 5339463 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.2250. Min Act: -0.1700

Data Index: 8068049 (Open Web Text)

Max Activating Token Index: 885

Text #3

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.1430. Min Act: -0.1700

Data Index: 3745262 (Open Web Text)

Max Activating Token Index: 892

Text #4

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.1338. Min Act: -0.1700

Data Index: 2526077 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 4.3773. Min Range: -4.3773

Max Act: 3.9864. Min Act: -0.1700

Data Index: 1046065 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.0650. Min Act: -0.1700

Data Index: 6767259 (Open Web Text)

Max Activating Token Index: 219

Text #7

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.0361. Min Act: -0.1700

Data Index: 5395151 (Open Web Text)

Max Activating Token Index: 913

Text #8

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.0241. Min Act: -0.1700

Data Index: 8139459 (Open Web Text)

Max Activating Token Index: 995

Text #9

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.0007. Min Act: -0.1700

Data Index: 4180277 (Open Web Text)

Max Activating Token Index: 806

Text #10

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.0018. Min Act: -0.1700

Data Index: 7688909 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.0365. Min Act: -0.1700

Data Index: 1233966 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 4.3773. Min Range: -4.3773

Max Act: 3.9593. Min Act: -0.1700

Data Index: 1490980 (Open Web Text)

Max Activating Token Index: 689

Text #13

Max Range: 4.3773. Min Range: -4.3773

Max Act: 4.0164. Min Act: -0.1700

Data Index: 8054357 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 4.3773. Min Range: -4.3773

Max Act: 3.9914. Min Act: -0.1700

Data Index: 8298995 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 4.3773. Min Range: -4.3773

Max Act: 3.9901. Min Act: -0.1700

Data Index: 3336126 (Open Web Text)

Max Activating Token Index: 612

Text #16

Max Range: 4.3773. Min Range: -4.3773

Max Act: 3.9057. Min Act: -0.1700

Data Index: 8382393 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 4.3773. Min Range: -4.3773

Max Act: 3.9732. Min Act: -0.1700

Data Index: 8178144 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 4.3773. Min Range: -4.3773

Max Act: 3.9760. Min Act: -0.1700

Data Index: 817969 (Open Web Text)

Max Activating Token Index: 848

Text #19

Max Range: 4.3773. Min Range: -4.3773

Max Act: 3.8789. Min Act: -0.1700

Data Index: 6797961 (Open Web Text)

Max Activating Token Index: 675