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

Dataset: Open Web Text

Neuron 2063 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: 4.8582. Min Range: -4.8582

Max Act: 4.8582. Min Act: -0.1700

Data Index: 4681915 (Open Web Text)

Max Activating Token Index: 667

Text #1

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.7701. Min Act: -0.1700

Data Index: 3975648 (Open Web Text)

Max Activating Token Index: 121

Text #2

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6290. Min Act: -0.1700

Data Index: 6880991 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6591. Min Act: -0.1700

Data Index: 6376644 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6408. Min Act: -0.1700

Data Index: 8214753 (Open Web Text)

Max Activating Token Index: 427

Text #5

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6724. Min Act: -0.1700

Data Index: 8517216 (Open Web Text)

Max Activating Token Index: 688

Text #6

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6701. Min Act: -0.1700

Data Index: 4440040 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6007. Min Act: -0.1700

Data Index: 689547 (Open Web Text)

Max Activating Token Index: 452

Text #8

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6194. Min Act: -0.1700

Data Index: 1497694 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6213. Min Act: -0.1700

Data Index: 8490307 (Open Web Text)

Max Activating Token Index: 777

Text #10

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5913. Min Act: -0.1700

Data Index: 2603214 (Open Web Text)

Max Activating Token Index: 618

Text #11

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5733. Min Act: -0.1700

Data Index: 1440125 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5738. Min Act: -0.1700

Data Index: 321242 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5689. Min Act: -0.1700

Data Index: 979018 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5863. Min Act: -0.1700

Data Index: 2644236 (Open Web Text)

Max Activating Token Index: 597

Text #15

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5512. Min Act: -0.1700

Data Index: 1735697 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5555. Min Act: -0.1700

Data Index: 3041049 (Open Web Text)

Max Activating Token Index: 909

Text #17

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5242. Min Act: -0.1700

Data Index: 7033137 (Open Web Text)

Max Activating Token Index: 241

Text #18

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5327. Min Act: -0.1700

Data Index: 3108283 (Open Web Text)

Max Activating Token Index: 476

Text #19

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5016. Min Act: -0.1700

Data Index: 5713684 (Open Web Text)

Max Activating Token Index: 842