Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 1924 in Layer 18

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3390. Min Act: -0.1700

Data Index: 663061 (Open Web Text)

Max Activating Token Index: 730

Text #1

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3390. Min Act: -0.1700

Data Index: 4772302 (Open Web Text)

Max Activating Token Index: 57

Text #2

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3077. Min Act: -0.1700

Data Index: 4737568 (Open Web Text)

Max Activating Token Index: 368

Text #3

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2452. Min Act: -0.1700

Data Index: 7909993 (Open Web Text)

Max Activating Token Index: 991

Text #4

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1827. Min Act: -0.1700

Data Index: 3767303 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2140. Min Act: -0.1700

Data Index: 8593094 (Open Web Text)

Max Activating Token Index: 775

Text #6

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1827. Min Act: -0.1700

Data Index: 126985 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1827. Min Act: -0.1700

Data Index: 3772097 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1515. Min Act: -0.1700

Data Index: 4405928 (Open Web Text)

Max Activating Token Index: 456

Text #9

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0890. Min Act: -0.1700

Data Index: 3652033 (Open Web Text)

Max Activating Token Index: 501

Text #10

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1202. Min Act: -0.1700

Data Index: 5056673 (Open Web Text)

Max Activating Token Index: 345

Text #11

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1202. Min Act: -0.1700

Data Index: 3088476 (Open Web Text)

Max Activating Token Index: 69

Text #12

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0890. Min Act: -0.1700

Data Index: 4446036 (Open Web Text)

Max Activating Token Index: 649

Text #13

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0890. Min Act: -0.1700

Data Index: 5951633 (Open Web Text)

Max Activating Token Index: 778

Text #14

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0265. Min Act: -0.1700

Data Index: 7734975 (Open Web Text)

Max Activating Token Index: 351

Text #15

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0577. Min Act: -0.1700

Data Index: 6054088 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0577. Min Act: -0.1700

Data Index: 5695526 (Open Web Text)

Max Activating Token Index: 164

Text #17

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0577. Min Act: -0.1700

Data Index: 8251541 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0577. Min Act: -0.1700

Data Index: 1116705 (Open Web Text)

Max Activating Token Index: 72

Text #19

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0265. Min Act: -0.1700

Data Index: 3670029 (Open Web Text)

Max Activating Token Index: 667