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

Dataset: Open Web Text

Neuron 1021 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: 1.5736. Min Range: -1.5736

Max Act: 1.5736. Min Act: -0.1700

Data Index: 4382689 (Open Web Text)

Max Activating Token Index: 830

Text #1

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5587. Min Act: -0.1700

Data Index: 5437132 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5461. Min Act: -0.1700

Data Index: 4107291 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5179. Min Act: -0.1700

Data Index: 8734880 (Open Web Text)

Max Activating Token Index: 808

Text #4

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4878. Min Act: -0.1700

Data Index: 8648302 (Open Web Text)

Max Activating Token Index: 854

Text #5

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4908. Min Act: -0.1700

Data Index: 4019377 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4905. Min Act: -0.1700

Data Index: 8734879 (Open Web Text)

Max Activating Token Index: 509

Text #7

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4833. Min Act: -0.1700

Data Index: 1786208 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4815. Min Act: -0.1700

Data Index: 3380617 (Open Web Text)

Max Activating Token Index: 913

Text #9

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4834. Min Act: -0.1699

Data Index: 6231463 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4705. Min Act: -0.1698

Data Index: 3894355 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4759. Min Act: -0.1698

Data Index: 8383261 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4758. Min Act: -0.1698

Data Index: 7017763 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4770. Min Act: -0.1700

Data Index: 2403647 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4717. Min Act: -0.1700

Data Index: 4182066 (Open Web Text)

Max Activating Token Index: 623

Text #15

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4604. Min Act: -0.1700

Data Index: 6022952 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4615. Min Act: -0.1697

Data Index: 1507947 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4595. Min Act: -0.1700

Data Index: 4529260 (Open Web Text)

Max Activating Token Index: 898

Text #18

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4486. Min Act: -0.1698

Data Index: 847530 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4505. Min Act: -0.1700

Data Index: 5669616 (Open Web Text)

Max Activating Token Index: 685