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

Dataset: Open Web Text

Neuron 2250 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: 1.8180. Min Range: -1.8180

Max Act: 1.8180. Min Act: -0.1700

Data Index: 615310 (Open Web Text)

Max Activating Token Index: 977

Text #1

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.7682. Min Act: -0.1700

Data Index: 5337695 (Open Web Text)

Max Activating Token Index: 754

Text #2

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.7586. Min Act: -0.1700

Data Index: 1190833 (Open Web Text)

Max Activating Token Index: 896

Text #3

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.7120. Min Act: -0.1700

Data Index: 1356614 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6964. Min Act: -0.1700

Data Index: 864085 (Open Web Text)

Max Activating Token Index: 501

Text #5

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6757. Min Act: -0.1700

Data Index: 3869816 (Open Web Text)

Max Activating Token Index: 78

Text #6

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6530. Min Act: -0.1700

Data Index: 8678433 (Open Web Text)

Max Activating Token Index: 571

Text #7

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6273. Min Act: -0.1700

Data Index: 7204439 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6294. Min Act: -0.1699

Data Index: 2806313 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6259. Min Act: -0.1700

Data Index: 7809613 (Open Web Text)

Max Activating Token Index: 146

Text #10

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6255. Min Act: -0.1700

Data Index: 827896 (Open Web Text)

Max Activating Token Index: 503

Text #11

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6262. Min Act: -0.1700

Data Index: 8201313 (Open Web Text)

Max Activating Token Index: 112

Text #12

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6205. Min Act: -0.1700

Data Index: 5722652 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6057. Min Act: -0.1700

Data Index: 7237388 (Open Web Text)

Max Activating Token Index: 977

Text #14

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6231. Min Act: -0.1700

Data Index: 938838 (Open Web Text)

Max Activating Token Index: 730

Text #15

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6140. Min Act: -0.1700

Data Index: 6944345 (Open Web Text)

Max Activating Token Index: 638

Text #16

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6110. Min Act: -0.1700

Data Index: 6697526 (Open Web Text)

Max Activating Token Index: 769

Text #17

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6110. Min Act: -0.1700

Data Index: 4377069 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6073. Min Act: -0.1700

Data Index: 1061260 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.5935. Min Act: -0.1700

Data Index: 2207999 (Open Web Text)

Max Activating Token Index: 401