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

Dataset: Open Web Text

Neuron 7 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: 0.7603. Min Range: -0.7603

Max Act: 0.7603. Min Act: -0.1700

Data Index: 6500643 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7529. Min Act: -0.1700

Data Index: 2559573 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7456. Min Act: -0.1700

Data Index: 8089738 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7353. Min Act: -0.1700

Data Index: 8614201 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7359. Min Act: -0.1700

Data Index: 6951429 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7389. Min Act: -0.1700

Data Index: 6942827 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7239. Min Act: -0.1700

Data Index: 5927465 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7192. Min Act: -0.1700

Data Index: 4554618 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7140. Min Act: -0.1700

Data Index: 3084214 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7185. Min Act: -0.1700

Data Index: 2166109 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7053. Min Act: -0.1700

Data Index: 2743746 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7101. Min Act: -0.1700

Data Index: 7708018 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7083. Min Act: -0.1700

Data Index: 4122427 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7076. Min Act: -0.1700

Data Index: 3998114 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7111. Min Act: -0.1700

Data Index: 2336109 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7084. Min Act: -0.1700

Data Index: 6543035 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7087. Min Act: -0.1700

Data Index: 2812451 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7054. Min Act: -0.1700

Data Index: 2051435 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7130. Min Act: -0.1700

Data Index: 6277303 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7100. Min Act: -0.1700

Data Index: 604444 (Open Web Text)

Max Activating Token Index: 8