Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 5547 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.3390. Min Act: -0.1700

Data Index: 4779058 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2596. Min Act: -0.1619

Data Index: 7469613 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2244. Min Act: -0.1669

Data Index: 4909413 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2156. Min Act: -0.1700

Data Index: 2951485 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2156. Min Act: -0.1700

Data Index: 640372 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2067. Min Act: -0.1700

Data Index: 7270081 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1979. Min Act: -0.1700

Data Index: 2516455 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1891. Min Act: -0.1700

Data Index: 133213 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1891. Min Act: -0.1699

Data Index: 5847577 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1891. Min Act: -0.1628

Data Index: 7469618 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1891. Min Act: -0.1699

Data Index: 4781516 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1715. Min Act: -0.1700

Data Index: 6825064 (Open Web Text)

Max Activating Token Index: 41

Text #12

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1540. Min Act: -0.1700

Data Index: 8137530 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1540. Min Act: -0.1700

Data Index: 1656876 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1452. Min Act: -0.1700

Data Index: 3920510 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1540. Min Act: -0.1700

Data Index: 1887726 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1628. Min Act: -0.1700

Data Index: 1893857 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1452. Min Act: -0.1700

Data Index: 4811738 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1452. Min Act: -0.1696

Data Index: 4909419 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1364. Min Act: -0.1700

Data Index: 2776431 (Open Web Text)

Max Activating Token Index: 678