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

Dataset: Open Web Text

Neuron 1873 in Layer 0

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: 3.2840. Min Range: -3.2840

Max Act: 3.2840. Min Act: -0.1700

Data Index: 1419156 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2424. Min Act: -0.1700

Data Index: 8390273 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2397. Min Act: -0.1700

Data Index: 6119873 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2240. Min Act: -0.1700

Data Index: 7884577 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2265. Min Act: -0.1700

Data Index: 7204386 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2301. Min Act: -0.1700

Data Index: 1248941 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2301. Min Act: -0.1700

Data Index: 4380090 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2301. Min Act: -0.1700

Data Index: 5608619 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2139. Min Act: -0.1700

Data Index: 5608620 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1956. Min Act: -0.1700

Data Index: 3407380 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1696. Min Act: -0.1700

Data Index: 6854623 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1492. Min Act: -0.1700

Data Index: 3303412 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1327. Min Act: -0.1700

Data Index: 512422 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1298. Min Act: -0.1700

Data Index: 7295902 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1200. Min Act: -0.1700

Data Index: 8338206 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1117. Min Act: -0.1700

Data Index: 48512 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0961. Min Act: -0.1700

Data Index: 3217517 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1039. Min Act: -0.1700

Data Index: 5548281 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0748. Min Act: -0.1700

Data Index: 3416723 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0753. Min Act: -0.1700

Data Index: 4836002 (Open Web Text)

Max Activating Token Index: 10