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

Dataset: Open Web Text

Neuron 2999 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: 1.5996. Min Range: -1.5996

Max Act: 1.5996. Min Act: -0.1700

Data Index: 6034237 (Open Web Text)

Max Activating Token Index: 656

Text #1

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5836. Min Act: -0.1700

Data Index: 3649850 (Open Web Text)

Max Activating Token Index: 86

Text #2

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5780. Min Act: -0.1697

Data Index: 1779943 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5421. Min Act: -0.1700

Data Index: 216899 (Open Web Text)

Max Activating Token Index: 533

Text #4

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5295. Min Act: -0.1700

Data Index: 8007309 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5271. Min Act: -0.1700

Data Index: 4750099 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5245. Min Act: -0.1700

Data Index: 1934259 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5093. Min Act: -0.1700

Data Index: 8574546 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5142. Min Act: -0.1699

Data Index: 1496837 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5029. Min Act: -0.1700

Data Index: 5293328 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5042. Min Act: -0.1700

Data Index: 3234108 (Open Web Text)

Max Activating Token Index: 96

Text #11

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4938. Min Act: -0.1700

Data Index: 1202120 (Open Web Text)

Max Activating Token Index: 586

Text #12

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4987. Min Act: -0.1700

Data Index: 2966820 (Open Web Text)

Max Activating Token Index: 627

Text #13

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4956. Min Act: -0.1700

Data Index: 2856686 (Open Web Text)

Max Activating Token Index: 570

Text #14

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4974. Min Act: -0.1700

Data Index: 3659033 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4978. Min Act: -0.1700

Data Index: 7082649 (Open Web Text)

Max Activating Token Index: 180

Text #16

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5063. Min Act: -0.1697

Data Index: 8499552 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4961. Min Act: -0.1700

Data Index: 1506110 (Open Web Text)

Max Activating Token Index: 623

Text #18

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4808. Min Act: -0.1699

Data Index: 5035884 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4849. Min Act: -0.1697

Data Index: 7289106 (Open Web Text)

Max Activating Token Index: 550