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

Dataset: Open Web Text

Neuron 805 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: 3.0812. Min Range: -3.0812

Max Act: 3.0812. Min Act: -0.1700

Data Index: 6504349 (Open Web Text)

Max Activating Token Index: 730

Text #1

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0569. Min Act: -0.1700

Data Index: 7736181 (Open Web Text)

Max Activating Token Index: 139

Text #2

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0397. Min Act: -0.1700

Data Index: 5002804 (Open Web Text)

Max Activating Token Index: 474

Text #3

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0403. Min Act: -0.1700

Data Index: 856945 (Open Web Text)

Max Activating Token Index: 507

Text #4

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0069. Min Act: -0.1700

Data Index: 3315259 (Open Web Text)

Max Activating Token Index: 761

Text #5

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0365. Min Act: -0.1700

Data Index: 3882860 (Open Web Text)

Max Activating Token Index: 779

Text #6

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0202. Min Act: -0.1700

Data Index: 6294351 (Open Web Text)

Max Activating Token Index: 421

Text #7

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0309. Min Act: -0.1700

Data Index: 5766121 (Open Web Text)

Max Activating Token Index: 320

Text #8

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0191. Min Act: -0.1700

Data Index: 5739886 (Open Web Text)

Max Activating Token Index: 822

Text #9

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0119. Min Act: -0.1700

Data Index: 8072995 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0149. Min Act: -0.1700

Data Index: 7699423 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 3.0812. Min Range: -3.0812

Max Act: 3.0034. Min Act: -0.1700

Data Index: 2182340 (Open Web Text)

Max Activating Token Index: 172

Text #12

Max Range: 3.0812. Min Range: -3.0812

Max Act: 2.9900. Min Act: -0.1700

Data Index: 7268597 (Open Web Text)

Max Activating Token Index: 535

Text #13

Max Range: 3.0812. Min Range: -3.0812

Max Act: 2.9837. Min Act: -0.1700

Data Index: 7072276 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 3.0812. Min Range: -3.0812

Max Act: 2.9596. Min Act: -0.1700

Data Index: 5136929 (Open Web Text)

Max Activating Token Index: 744

Text #15

Max Range: 3.0812. Min Range: -3.0812

Max Act: 2.9680. Min Act: -0.1700

Data Index: 8550849 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 3.0812. Min Range: -3.0812

Max Act: 2.9447. Min Act: -0.1700

Data Index: 5550247 (Open Web Text)

Max Activating Token Index: 271

Text #17

Max Range: 3.0812. Min Range: -3.0812

Max Act: 2.9471. Min Act: -0.1700

Data Index: 6844112 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 3.0812. Min Range: -3.0812

Max Act: 2.9047. Min Act: -0.1700

Data Index: 667266 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 3.0812. Min Range: -3.0812

Max Act: 2.9190. Min Act: -0.1700

Data Index: 4415057 (Open Web Text)

Max Activating Token Index: 35