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

Dataset: Open Web Text

Neuron 2030 in Layer 2

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: 2.5067. Min Range: -2.5067

Max Act: 2.4945. Min Act: -0.1700

Data Index: 864718 (Open Web Text)

Max Activating Token Index: 77

Text #1

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.5067. Min Act: -0.1700

Data Index: 6897011 (Open Web Text)

Max Activating Token Index: 885

Text #2

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.5012. Min Act: -0.1700

Data Index: 5349532 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.4471. Min Act: -0.1700

Data Index: 72975 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.4439. Min Act: -0.1700

Data Index: 1563900 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.4522. Min Act: -0.1700

Data Index: 5294810 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.4395. Min Act: -0.1699

Data Index: 3070919 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.4258. Min Act: -0.1700

Data Index: 2692256 (Open Web Text)

Max Activating Token Index: 205

Text #8

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.4181. Min Act: -0.1700

Data Index: 8588988 (Open Web Text)

Max Activating Token Index: 645

Text #9

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.4250. Min Act: -0.1700

Data Index: 5388330 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.4041. Min Act: -0.1700

Data Index: 6834849 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3985. Min Act: -0.1700

Data Index: 7399289 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3904. Min Act: -0.1700

Data Index: 2533863 (Open Web Text)

Max Activating Token Index: 128

Text #13

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3819. Min Act: -0.1700

Data Index: 4055429 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3957. Min Act: -0.1700

Data Index: 6582893 (Open Web Text)

Max Activating Token Index: 92

Text #15

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3739. Min Act: -0.1700

Data Index: 3250400 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3808. Min Act: -0.1700

Data Index: 4271513 (Open Web Text)

Max Activating Token Index: 57

Text #17

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3742. Min Act: -0.1700

Data Index: 2553294 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3683. Min Act: -0.1700

Data Index: 6000939 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 2.5067. Min Range: -2.5067

Max Act: 2.3715. Min Act: -0.1700

Data Index: 1108998 (Open Web Text)

Max Activating Token Index: 81