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

Dataset: Open Web Text

Neuron 1043 in Layer 0

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: 4.5472. Min Range: -4.5472

Max Act: 4.5472. Min Act: -0.1700

Data Index: 6800341 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.4945. Min Act: -0.1700

Data Index: 1639395 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.5102. Min Act: -0.1700

Data Index: 6987833 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.5072. Min Act: -0.1700

Data Index: 2330988 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.4567. Min Act: -0.1700

Data Index: 2437018 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.4022. Min Act: -0.1700

Data Index: 2032965 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3910. Min Act: -0.1700

Data Index: 5621421 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3921. Min Act: -0.1700

Data Index: 6714970 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3771. Min Act: -0.1700

Data Index: 3618570 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3697. Min Act: -0.1700

Data Index: 5035338 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3826. Min Act: -0.1700

Data Index: 8725524 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3838. Min Act: -0.1700

Data Index: 1041654 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3773. Min Act: -0.1700

Data Index: 7942890 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3568. Min Act: -0.1700

Data Index: 5354858 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3580. Min Act: -0.1700

Data Index: 3888764 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3838. Min Act: -0.1700

Data Index: 6665886 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3357. Min Act: -0.1700

Data Index: 3197463 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3236. Min Act: -0.1700

Data Index: 5055456 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3397. Min Act: -0.1700

Data Index: 674659 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.5472. Min Range: -4.5472

Max Act: 4.3301. Min Act: -0.1700

Data Index: 8288772 (Open Web Text)

Max Activating Token Index: 4