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

Dataset: Open Web Text

Neuron 1743 in Layer 4

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: 3.3416. Min Range: -3.3416

Max Act: 3.3416. Min Act: -0.1700

Data Index: 6397683 (Open Web Text)

Max Activating Token Index: 1018

Text #1

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.3057. Min Act: -0.1700

Data Index: 6117404 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2784. Min Act: -0.1700

Data Index: 6713965 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2741. Min Act: -0.1700

Data Index: 4947387 (Open Web Text)

Max Activating Token Index: 73

Text #4

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2611. Min Act: -0.1700

Data Index: 7571792 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2233. Min Act: -0.1700

Data Index: 3255812 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2221. Min Act: -0.1700

Data Index: 1448646 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2100. Min Act: -0.1700

Data Index: 645335 (Open Web Text)

Max Activating Token Index: 327

Text #8

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2058. Min Act: -0.1700

Data Index: 6420654 (Open Web Text)

Max Activating Token Index: 557

Text #9

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2017. Min Act: -0.1700

Data Index: 4326011 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2019. Min Act: -0.1700

Data Index: 5141620 (Open Web Text)

Max Activating Token Index: 889

Text #11

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2034. Min Act: -0.1700

Data Index: 6261292 (Open Web Text)

Max Activating Token Index: 757

Text #12

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1974. Min Act: -0.1700

Data Index: 7506160 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2095. Min Act: -0.1700

Data Index: 7361536 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2112. Min Act: -0.1700

Data Index: 3531412 (Open Web Text)

Max Activating Token Index: 205

Text #15

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1774. Min Act: -0.1700

Data Index: 3914864 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1805. Min Act: -0.1700

Data Index: 5251501 (Open Web Text)

Max Activating Token Index: 845

Text #17

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2100. Min Act: -0.1700

Data Index: 1229803 (Open Web Text)

Max Activating Token Index: 898

Text #18

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1846. Min Act: -0.1700

Data Index: 4518446 (Open Web Text)

Max Activating Token Index: 147

Text #19

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1817. Min Act: -0.1700

Data Index: 5471264 (Open Web Text)

Max Activating Token Index: 32