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

Dataset: Open Web Text

Neuron 1054 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: 4.0584. Min Range: -4.0584

Max Act: 4.0412. Min Act: -0.1700

Data Index: 7161626 (Open Web Text)

Max Activating Token Index: 880

Text #1

Max Range: 4.0584. Min Range: -4.0584

Max Act: 4.0584. Min Act: -0.1700

Data Index: 1512277 (Open Web Text)

Max Activating Token Index: 1002

Text #2

Max Range: 4.0584. Min Range: -4.0584

Max Act: 4.0447. Min Act: -0.1700

Data Index: 5396795 (Open Web Text)

Max Activating Token Index: 998

Text #3

Max Range: 4.0584. Min Range: -4.0584

Max Act: 4.0394. Min Act: -0.1700

Data Index: 5926038 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9934. Min Act: -0.1700

Data Index: 8462403 (Open Web Text)

Max Activating Token Index: 96

Text #5

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9659. Min Act: -0.1700

Data Index: 8167323 (Open Web Text)

Max Activating Token Index: 326

Text #6

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9592. Min Act: -0.1700

Data Index: 359222 (Open Web Text)

Max Activating Token Index: 156

Text #7

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9555. Min Act: -0.1700

Data Index: 3151757 (Open Web Text)

Max Activating Token Index: 710

Text #8

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9750. Min Act: -0.1700

Data Index: 6661468 (Open Web Text)

Max Activating Token Index: 695

Text #9

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9357. Min Act: -0.1700

Data Index: 6434361 (Open Web Text)

Max Activating Token Index: 265

Text #10

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9144. Min Act: -0.1700

Data Index: 3657264 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9303. Min Act: -0.1700

Data Index: 2905449 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9359. Min Act: -0.1700

Data Index: 8220433 (Open Web Text)

Max Activating Token Index: 465

Text #13

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9410. Min Act: -0.1700

Data Index: 6059824 (Open Web Text)

Max Activating Token Index: 743

Text #14

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9319. Min Act: -0.1700

Data Index: 4656448 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.8944. Min Act: -0.1700

Data Index: 8264564 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.8877. Min Act: -0.1700

Data Index: 1823293 (Open Web Text)

Max Activating Token Index: 254

Text #17

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.8955. Min Act: -0.1700

Data Index: 1772757 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.9074. Min Act: -0.1700

Data Index: 4362714 (Open Web Text)

Max Activating Token Index: 226

Text #19

Max Range: 4.0584. Min Range: -4.0584

Max Act: 3.8992. Min Act: -0.1700

Data Index: 2182342 (Open Web Text)

Max Activating Token Index: 830