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

Dataset: Open Web Text

Neuron 630 in Layer 1

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: 1.4651. Min Range: -1.4651

Max Act: 1.4651. Min Act: -0.1700

Data Index: 2157766 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4558. Min Act: -0.1677

Data Index: 2518840 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4328. Min Act: -0.1680

Data Index: 7794928 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4097. Min Act: -0.1700

Data Index: 1216597 (Open Web Text)

Max Activating Token Index: 982

Text #4

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4010. Min Act: -0.1699

Data Index: 2933191 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3929. Min Act: -0.1699

Data Index: 1486183 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4003. Min Act: -0.1700

Data Index: 4328634 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3938. Min Act: -0.1686

Data Index: 2015902 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3939. Min Act: -0.1700

Data Index: 6003399 (Open Web Text)

Max Activating Token Index: 655

Text #9

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3959. Min Act: -0.1700

Data Index: 4073796 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3910. Min Act: -0.1510

Data Index: 8268967 (Open Web Text)

Max Activating Token Index: 259

Text #11

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3959. Min Act: -0.1695

Data Index: 4717840 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3805. Min Act: -0.1700

Data Index: 8395859 (Open Web Text)

Max Activating Token Index: 350

Text #13

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3870. Min Act: -0.1700

Data Index: 7245593 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3959. Min Act: -0.1698

Data Index: 1452758 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3852. Min Act: -0.1659

Data Index: 3926846 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3959. Min Act: -0.1699

Data Index: 2876887 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3723. Min Act: -0.1700

Data Index: 4125165 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3711. Min Act: -0.1700

Data Index: 6069140 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3615. Min Act: -0.1700

Data Index: 6964437 (Open Web Text)

Max Activating Token Index: 950