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

Dataset: Open Web Text

Neuron 470 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: 1.8360. Min Range: -1.8360

Max Act: 1.8360. Min Act: -0.1700

Data Index: 6839987 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8161. Min Act: -0.1700

Data Index: 445376 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1303761 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8092. Min Act: -0.1700

Data Index: 8590930 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8100. Min Act: -0.1700

Data Index: 7318595 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8154. Min Act: -0.1700

Data Index: 6787480 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8046. Min Act: -0.1700

Data Index: 6397480 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8141. Min Act: -0.1700

Data Index: 2292180 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8010. Min Act: -0.1700

Data Index: 1500196 (Open Web Text)

Max Activating Token Index: 933

Text #9

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7991. Min Act: -0.1700

Data Index: 4184366 (Open Web Text)

Max Activating Token Index: 62

Text #10

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7858. Min Act: -0.1700

Data Index: 8477469 (Open Web Text)

Max Activating Token Index: 57

Text #11

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7868. Min Act: -0.1700

Data Index: 4265736 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7837. Min Act: -0.1700

Data Index: 552640 (Open Web Text)

Max Activating Token Index: 490

Text #13

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7889. Min Act: -0.1700

Data Index: 3630934 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7820. Min Act: -0.1700

Data Index: 3607494 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7760. Min Act: -0.1700

Data Index: 1657395 (Open Web Text)

Max Activating Token Index: 70

Text #16

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7754. Min Act: -0.1700

Data Index: 4200934 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7785. Min Act: -0.1700

Data Index: 5758673 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7820. Min Act: -0.1700

Data Index: 6338454 (Open Web Text)

Max Activating Token Index: 94

Text #19

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.7799. Min Act: -0.1700

Data Index: 73884 (Open Web Text)

Max Activating Token Index: 4