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

Dataset: Open Web Text

Neuron 2555 in Layer 5

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: 3.2812. Min Range: -3.2812

Max Act: 3.2812. Min Act: -0.1700

Data Index: 2868081 (Open Web Text)

Max Activating Token Index: 413

Text #1

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.2247. Min Act: -0.1700

Data Index: 7149849 (Open Web Text)

Max Activating Token Index: 356

Text #2

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.1908. Min Act: -0.1700

Data Index: 2432746 (Open Web Text)

Max Activating Token Index: 422

Text #3

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.1669. Min Act: -0.1700

Data Index: 3587914 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.1367. Min Act: -0.1700

Data Index: 8624998 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.1304. Min Act: -0.1700

Data Index: 815580 (Open Web Text)

Max Activating Token Index: 991

Text #6

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.1107. Min Act: -0.1700

Data Index: 4333650 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0980. Min Act: -0.1700

Data Index: 5276765 (Open Web Text)

Max Activating Token Index: 346

Text #8

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0914. Min Act: -0.1700

Data Index: 4219983 (Open Web Text)

Max Activating Token Index: 883

Text #9

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.1309. Min Act: -0.1700

Data Index: 3444190 (Open Web Text)

Max Activating Token Index: 653

Text #10

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0853. Min Act: -0.1700

Data Index: 8714688 (Open Web Text)

Max Activating Token Index: 586

Text #11

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0641. Min Act: -0.1700

Data Index: 697534 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0747. Min Act: -0.1700

Data Index: 5366533 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0848. Min Act: -0.1700

Data Index: 5874345 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0759. Min Act: -0.1700

Data Index: 2113922 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.1025. Min Act: -0.1700

Data Index: 3091890 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0486. Min Act: -0.1700

Data Index: 1866719 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0444. Min Act: -0.1700

Data Index: 3143687 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0265. Min Act: -0.1700

Data Index: 6717521 (Open Web Text)

Max Activating Token Index: 707

Text #19

Max Range: 3.2812. Min Range: -3.2812

Max Act: 3.0520. Min Act: -0.1700

Data Index: 7795807 (Open Web Text)

Max Activating Token Index: 434