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

Dataset: Open Web Text

Neuron 643 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: 1.6854. Min Range: -1.6854

Max Act: 1.6854. Min Act: -0.1700

Data Index: 7054974 (Open Web Text)

Max Activating Token Index: 585

Text #1

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6845. Min Act: -0.1700

Data Index: 7067264 (Open Web Text)

Max Activating Token Index: 134

Text #2

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6453. Min Act: -0.1700

Data Index: 7054986 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6297. Min Act: -0.1700

Data Index: 7029324 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6275. Min Act: -0.1700

Data Index: 2208116 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6316. Min Act: -0.1700

Data Index: 2224385 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6241. Min Act: -0.1700

Data Index: 812120 (Open Web Text)

Max Activating Token Index: 177

Text #7

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5999. Min Act: -0.1700

Data Index: 1263729 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5974. Min Act: -0.1700

Data Index: 923878 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5928. Min Act: -0.1700

Data Index: 5513520 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6042. Min Act: -0.1700

Data Index: 3430914 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5969. Min Act: -0.1700

Data Index: 8607715 (Open Web Text)

Max Activating Token Index: 220

Text #12

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6047. Min Act: -0.1700

Data Index: 5168239 (Open Web Text)

Max Activating Token Index: 851

Text #13

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5959. Min Act: -0.1700

Data Index: 3884602 (Open Web Text)

Max Activating Token Index: 217

Text #14

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5870. Min Act: -0.1700

Data Index: 1270086 (Open Web Text)

Max Activating Token Index: 118

Text #15

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5889. Min Act: -0.1700

Data Index: 6096834 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5967. Min Act: -0.1700

Data Index: 7826886 (Open Web Text)

Max Activating Token Index: 225

Text #17

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5737. Min Act: -0.1700

Data Index: 3207387 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5789. Min Act: -0.1700

Data Index: 3732312 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5826. Min Act: -0.1700

Data Index: 3232991 (Open Web Text)

Max Activating Token Index: 79