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

Dataset: Open Web Text

Neuron 2159 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: 2.5696. Min Range: -2.5696

Max Act: 2.5654. Min Act: -0.1700

Data Index: 5884976 (Open Web Text)

Max Activating Token Index: 907

Text #1

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.5696. Min Act: -0.1700

Data Index: 4120853 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.5204. Min Act: -0.1700

Data Index: 2910626 (Open Web Text)

Max Activating Token Index: 309

Text #3

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.5029. Min Act: -0.1700

Data Index: 6417427 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4926. Min Act: -0.1700

Data Index: 2819200 (Open Web Text)

Max Activating Token Index: 865

Text #5

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4765. Min Act: -0.1700

Data Index: 509587 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4797. Min Act: -0.1700

Data Index: 7721584 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4937. Min Act: -0.1700

Data Index: 3146965 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4769. Min Act: -0.1700

Data Index: 6115051 (Open Web Text)

Max Activating Token Index: 70

Text #9

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4822. Min Act: -0.1700

Data Index: 1834536 (Open Web Text)

Max Activating Token Index: 555

Text #10

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4594. Min Act: -0.1700

Data Index: 6602218 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4741. Min Act: -0.1700

Data Index: 5475570 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4574. Min Act: -0.1700

Data Index: 4729815 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4418. Min Act: -0.1700

Data Index: 3003845 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4401. Min Act: -0.1700

Data Index: 5470876 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4459. Min Act: -0.1700

Data Index: 7528801 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4324. Min Act: -0.1700

Data Index: 5222091 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4161. Min Act: -0.1700

Data Index: 1328183 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4089. Min Act: -0.1700

Data Index: 3736737 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 2.5696. Min Range: -2.5696

Max Act: 2.4255. Min Act: -0.1700

Data Index: 4729466 (Open Web Text)

Max Activating Token Index: 4