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

Dataset: Open Web Text

Neuron 2089 in Layer 3

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: 4.3103. Min Range: -4.3103

Max Act: 4.3103. Min Act: -0.1700

Data Index: 1854057 (Open Web Text)

Max Activating Token Index: 849

Text #1

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.2568. Min Act: -0.1700

Data Index: 5399308 (Open Web Text)

Max Activating Token Index: 711

Text #2

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.2376. Min Act: -0.1700

Data Index: 7393390 (Open Web Text)

Max Activating Token Index: 916

Text #3

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.2162. Min Act: -0.1700

Data Index: 431757 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.2014. Min Act: -0.1700

Data Index: 3591889 (Open Web Text)

Max Activating Token Index: 896

Text #5

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1665. Min Act: -0.1700

Data Index: 8220448 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1738. Min Act: -0.1700

Data Index: 2857199 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1700. Min Act: -0.1700

Data Index: 2893976 (Open Web Text)

Max Activating Token Index: 455

Text #8

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1948. Min Act: -0.1700

Data Index: 1111172 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1527. Min Act: -0.1700

Data Index: 3989618 (Open Web Text)

Max Activating Token Index: 467

Text #10

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1428. Min Act: -0.1700

Data Index: 4920810 (Open Web Text)

Max Activating Token Index: 626

Text #11

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1232. Min Act: -0.1700

Data Index: 1487480 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1349. Min Act: -0.1700

Data Index: 5722149 (Open Web Text)

Max Activating Token Index: 173

Text #13

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.0892. Min Act: -0.1700

Data Index: 4272729 (Open Web Text)

Max Activating Token Index: 563

Text #14

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1598. Min Act: -0.1700

Data Index: 8153536 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1858. Min Act: -0.1700

Data Index: 7220115 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1070. Min Act: -0.1700

Data Index: 2950396 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.0788. Min Act: -0.1700

Data Index: 2788902 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.1501. Min Act: -0.1700

Data Index: 4793071 (Open Web Text)

Max Activating Token Index: 405

Text #19

Max Range: 4.3103. Min Range: -4.3103

Max Act: 4.0696. Min Act: -0.1700

Data Index: 3941078 (Open Web Text)

Max Activating Token Index: 338