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

Dataset: Open Web Text

Neuron 2586 in Layer 6

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: 6.1810. Min Range: -6.1810

Max Act: 6.1810. Min Act: -0.1700

Data Index: 4609218 (Open Web Text)

Max Activating Token Index: 342

Text #1

Max Range: 6.1810. Min Range: -6.1810

Max Act: 6.0824. Min Act: -0.1700

Data Index: 5723293 (Open Web Text)

Max Activating Token Index: 823

Text #2

Max Range: 6.1810. Min Range: -6.1810

Max Act: 6.0055. Min Act: -0.1700

Data Index: 816904 (Open Web Text)

Max Activating Token Index: 246

Text #3

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.9418. Min Act: -0.1700

Data Index: 6560338 (Open Web Text)

Max Activating Token Index: 766

Text #4

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.9347. Min Act: -0.1700

Data Index: 6863731 (Open Web Text)

Max Activating Token Index: 260

Text #5

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.9233. Min Act: -0.1700

Data Index: 1400974 (Open Web Text)

Max Activating Token Index: 961

Text #6

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8697. Min Act: -0.1700

Data Index: 4376674 (Open Web Text)

Max Activating Token Index: 293

Text #7

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8266. Min Act: -0.1700

Data Index: 7614626 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.9017. Min Act: -0.1700

Data Index: 3405715 (Open Web Text)

Max Activating Token Index: 204

Text #9

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8917. Min Act: -0.1700

Data Index: 1952058 (Open Web Text)

Max Activating Token Index: 255

Text #10

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.9000. Min Act: -0.1700

Data Index: 5270037 (Open Web Text)

Max Activating Token Index: 886

Text #11

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8531. Min Act: -0.1700

Data Index: 7391833 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8410. Min Act: -0.1700

Data Index: 7425078 (Open Web Text)

Max Activating Token Index: 857

Text #13

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8334. Min Act: -0.1700

Data Index: 7643186 (Open Web Text)

Max Activating Token Index: 223

Text #14

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8995. Min Act: -0.1700

Data Index: 1674495 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.9046. Min Act: -0.1700

Data Index: 477844 (Open Web Text)

Max Activating Token Index: 961

Text #16

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8381. Min Act: -0.1700

Data Index: 6464026 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8351. Min Act: -0.1700

Data Index: 521799 (Open Web Text)

Max Activating Token Index: 376

Text #18

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.8043. Min Act: -0.1700

Data Index: 5232084 (Open Web Text)

Max Activating Token Index: 450

Text #19

Max Range: 6.1810. Min Range: -6.1810

Max Act: 5.7984. Min Act: -0.1700

Data Index: 7373068 (Open Web Text)

Max Activating Token Index: 204