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

Dataset: Open Web Text

Neuron 590 in Layer 1

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: 2.8118. Min Range: -2.8118

Max Act: 2.8118. Min Act: -0.1700

Data Index: 741032 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.6025. Min Act: -0.1700

Data Index: 5133718 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.6060. Min Act: -0.1700

Data Index: 8694785 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5828. Min Act: -0.1700

Data Index: 5538355 (Open Web Text)

Max Activating Token Index: 319

Text #4

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5722. Min Act: -0.1700

Data Index: 4194163 (Open Web Text)

Max Activating Token Index: 572

Text #5

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5718. Min Act: -0.1700

Data Index: 4383155 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5647. Min Act: -0.1700

Data Index: 4053312 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5709. Min Act: -0.1700

Data Index: 2902242 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5558. Min Act: -0.1700

Data Index: 3011099 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5752. Min Act: -0.1700

Data Index: 217006 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5659. Min Act: -0.1700

Data Index: 3800969 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5645. Min Act: -0.1700

Data Index: 8223462 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5692. Min Act: -0.1700

Data Index: 5621238 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5591. Min Act: -0.1700

Data Index: 3581393 (Open Web Text)

Max Activating Token Index: 747

Text #14

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5516. Min Act: -0.1700

Data Index: 2982002 (Open Web Text)

Max Activating Token Index: 604

Text #15

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5282. Min Act: -0.1700

Data Index: 2422840 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5397. Min Act: -0.1700

Data Index: 917763 (Open Web Text)

Max Activating Token Index: 666

Text #17

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5391. Min Act: -0.1700

Data Index: 2982004 (Open Web Text)

Max Activating Token Index: 566

Text #18

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5382. Min Act: -0.1700

Data Index: 2616281 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.8118. Min Range: -2.8118

Max Act: 2.5103. Min Act: -0.1700

Data Index: 2981999 (Open Web Text)

Max Activating Token Index: 206