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

Dataset: Open Web Text

Neuron 3027 in Layer 2

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: 3.1777. Min Range: -3.1777

Max Act: 3.1777. Min Act: -0.1700

Data Index: 1648020 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.1563. Min Act: -0.1700

Data Index: 5799465 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.1200. Min Act: -0.1700

Data Index: 186680 (Open Web Text)

Max Activating Token Index: 91

Text #3

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0909. Min Act: -0.1700

Data Index: 8253153 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0500. Min Act: -0.1700

Data Index: 3186839 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0375. Min Act: -0.1700

Data Index: 7521639 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0610. Min Act: -0.1700

Data Index: 5771019 (Open Web Text)

Max Activating Token Index: 344

Text #7

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0452. Min Act: -0.1700

Data Index: 2564631 (Open Web Text)

Max Activating Token Index: 581

Text #8

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0517. Min Act: -0.1700

Data Index: 5444739 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0536. Min Act: -0.1700

Data Index: 1565918 (Open Web Text)

Max Activating Token Index: 813

Text #10

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0447. Min Act: -0.1700

Data Index: 2587967 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0438. Min Act: -0.1700

Data Index: 7747705 (Open Web Text)

Max Activating Token Index: 93

Text #12

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0265. Min Act: -0.1700

Data Index: 156107 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0271. Min Act: -0.1700

Data Index: 650265 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0279. Min Act: -0.1700

Data Index: 78854 (Open Web Text)

Max Activating Token Index: 89

Text #15

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0194. Min Act: -0.1700

Data Index: 4865356 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0184. Min Act: -0.1700

Data Index: 3242922 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0526. Min Act: -0.1700

Data Index: 4851953 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0075. Min Act: -0.1700

Data Index: 5588438 (Open Web Text)

Max Activating Token Index: 167

Text #19

Max Range: 3.1777. Min Range: -3.1777

Max Act: 3.0194. Min Act: -0.1700

Data Index: 4548074 (Open Web Text)

Max Activating Token Index: 23