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

Dataset: Open Web Text

Neuron 47 in Layer 3

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: 4.0013. Min Range: -4.0013

Max Act: 4.0013. Min Act: -0.1700

Data Index: 6723205 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8661. Min Act: -0.1700

Data Index: 2461886 (Open Web Text)

Max Activating Token Index: 748

Text #2

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8256. Min Act: -0.1700

Data Index: 7741776 (Open Web Text)

Max Activating Token Index: 693

Text #3

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8318. Min Act: -0.1700

Data Index: 4934662 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8329. Min Act: -0.1700

Data Index: 610126 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8201. Min Act: -0.1700

Data Index: 6661682 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7874. Min Act: -0.1700

Data Index: 1673187 (Open Web Text)

Max Activating Token Index: 952

Text #7

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7926. Min Act: -0.1700

Data Index: 7937032 (Open Web Text)

Max Activating Token Index: 606

Text #8

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8104. Min Act: -0.1700

Data Index: 215864 (Open Web Text)

Max Activating Token Index: 329

Text #9

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7989. Min Act: -0.1700

Data Index: 5712027 (Open Web Text)

Max Activating Token Index: 30

Text #10

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7897. Min Act: -0.1700

Data Index: 1023617 (Open Web Text)

Max Activating Token Index: 974

Text #11

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7720. Min Act: -0.1700

Data Index: 7271875 (Open Web Text)

Max Activating Token Index: 578

Text #12

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8001. Min Act: -0.1700

Data Index: 3623845 (Open Web Text)

Max Activating Token Index: 502

Text #13

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7843. Min Act: -0.1700

Data Index: 5944407 (Open Web Text)

Max Activating Token Index: 172

Text #14

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7941. Min Act: -0.1700

Data Index: 3792553 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7817. Min Act: -0.1700

Data Index: 1655933 (Open Web Text)

Max Activating Token Index: 715

Text #16

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7544. Min Act: -0.1700

Data Index: 1512825 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7848. Min Act: -0.1700

Data Index: 247139 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7661. Min Act: -0.1700

Data Index: 7724263 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7835. Min Act: -0.1700

Data Index: 789348 (Open Web Text)

Max Activating Token Index: 33