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

Dataset: Open Web Text

Neuron 1912 in Layer 4

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: 4.0663. Min Range: -4.0663

Max Act: 4.0663. Min Act: -0.1700

Data Index: 7474326 (Open Web Text)

Max Activating Token Index: 431

Text #1

Max Range: 4.0663. Min Range: -4.0663

Max Act: 4.0254. Min Act: -0.1700

Data Index: 8178114 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 4.0663. Min Range: -4.0663

Max Act: 4.0178. Min Act: -0.1700

Data Index: 5342502 (Open Web Text)

Max Activating Token Index: 389

Text #3

Max Range: 4.0663. Min Range: -4.0663

Max Act: 4.0073. Min Act: -0.1700

Data Index: 4931387 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 4.0663. Min Range: -4.0663

Max Act: 4.0272. Min Act: -0.1700

Data Index: 4483030 (Open Web Text)

Max Activating Token Index: 162

Text #5

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9728. Min Act: -0.1700

Data Index: 4625244 (Open Web Text)

Max Activating Token Index: 427

Text #6

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9999. Min Act: -0.1700

Data Index: 4294896 (Open Web Text)

Max Activating Token Index: 1010

Text #7

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9071. Min Act: -0.1700

Data Index: 6500737 (Open Web Text)

Max Activating Token Index: 748

Text #8

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8919. Min Act: -0.1700

Data Index: 2983732 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9055. Min Act: -0.1700

Data Index: 209075 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9022. Min Act: -0.1700

Data Index: 6458596 (Open Web Text)

Max Activating Token Index: 831

Text #11

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8841. Min Act: -0.1700

Data Index: 7113004 (Open Web Text)

Max Activating Token Index: 78

Text #12

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8963. Min Act: -0.1700

Data Index: 2154743 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9046. Min Act: -0.1700

Data Index: 4184752 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8600. Min Act: -0.1700

Data Index: 5364151 (Open Web Text)

Max Activating Token Index: 653

Text #15

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8901. Min Act: -0.1700

Data Index: 2485925 (Open Web Text)

Max Activating Token Index: 550

Text #16

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8475. Min Act: -0.1700

Data Index: 2559987 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8356. Min Act: -0.1700

Data Index: 6947955 (Open Web Text)

Max Activating Token Index: 243

Text #18

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8624. Min Act: -0.1700

Data Index: 7101499 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8397. Min Act: -0.1700

Data Index: 2264868 (Open Web Text)

Max Activating Token Index: 419