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

Dataset: Open Web Text

Neuron 2428 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: 2.0844. Min Range: -2.0844

Max Act: 2.0844. Min Act: -0.1696

Data Index: 7889091 (Open Web Text)

Max Activating Token Index: 897

Text #1

Max Range: 2.0844. Min Range: -2.0844

Max Act: 2.0202. Min Act: -0.1700

Data Index: 2805355 (Open Web Text)

Max Activating Token Index: 125

Text #2

Max Range: 2.0844. Min Range: -2.0844

Max Act: 2.0188. Min Act: -0.1606

Data Index: 981457 (Open Web Text)

Max Activating Token Index: 784

Text #3

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.9930. Min Act: -0.1700

Data Index: 4634282 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.9332. Min Act: -0.1690

Data Index: 301661 (Open Web Text)

Max Activating Token Index: 680

Text #5

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.9263. Min Act: -0.1699

Data Index: 5423801 (Open Web Text)

Max Activating Token Index: 722

Text #6

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.9396. Min Act: -0.1696

Data Index: 1014546 (Open Web Text)

Max Activating Token Index: 740

Text #7

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.9273. Min Act: -0.1606

Data Index: 6580633 (Open Web Text)

Max Activating Token Index: 735

Text #8

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8984. Min Act: -0.1700

Data Index: 3553934 (Open Web Text)

Max Activating Token Index: 224

Text #9

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8837. Min Act: -0.1700

Data Index: 6370140 (Open Web Text)

Max Activating Token Index: 958

Text #10

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8874. Min Act: -0.1699

Data Index: 5202906 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8280. Min Act: -0.1690

Data Index: 1068717 (Open Web Text)

Max Activating Token Index: 964

Text #12

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8282. Min Act: -0.1700

Data Index: 7780108 (Open Web Text)

Max Activating Token Index: 335

Text #13

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8257. Min Act: -0.1695

Data Index: 8628573 (Open Web Text)

Max Activating Token Index: 839

Text #14

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8301. Min Act: -0.1700

Data Index: 6418919 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8197. Min Act: -0.1666

Data Index: 5739931 (Open Web Text)

Max Activating Token Index: 763

Text #16

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8158. Min Act: -0.1681

Data Index: 5006668 (Open Web Text)

Max Activating Token Index: 804

Text #17

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8181. Min Act: -0.1688

Data Index: 7119800 (Open Web Text)

Max Activating Token Index: 933

Text #18

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8160. Min Act: -0.1635

Data Index: 121585 (Open Web Text)

Max Activating Token Index: 734

Text #19

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.8024. Min Act: -0.1700

Data Index: 1025543 (Open Web Text)

Max Activating Token Index: 442