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

Dataset: Open Web Text

Neuron 727 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: 4.0156. Min Range: -4.0156

Max Act: 4.0156. Min Act: -0.1700

Data Index: 4235173 (Open Web Text)

Max Activating Token Index: 37

Text #1

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8559. Min Act: -0.1700

Data Index: 7757340 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8596. Min Act: -0.1700

Data Index: 5482630 (Open Web Text)

Max Activating Token Index: 876

Text #3

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8357. Min Act: -0.1700

Data Index: 6286323 (Open Web Text)

Max Activating Token Index: 391

Text #4

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8173. Min Act: -0.1700

Data Index: 3243440 (Open Web Text)

Max Activating Token Index: 568

Text #5

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8294. Min Act: -0.1700

Data Index: 4505367 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8329. Min Act: -0.1700

Data Index: 8644032 (Open Web Text)

Max Activating Token Index: 158

Text #7

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8346. Min Act: -0.1700

Data Index: 5298511 (Open Web Text)

Max Activating Token Index: 956

Text #8

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.7891. Min Act: -0.1700

Data Index: 7491225 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.7805. Min Act: -0.1700

Data Index: 247554 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8021. Min Act: -0.1700

Data Index: 4216918 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.7927. Min Act: -0.1700

Data Index: 6102738 (Open Web Text)

Max Activating Token Index: 44

Text #12

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8445. Min Act: -0.1700

Data Index: 2154004 (Open Web Text)

Max Activating Token Index: 447

Text #13

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.7852. Min Act: -0.1700

Data Index: 8252323 (Open Web Text)

Max Activating Token Index: 162

Text #14

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8017. Min Act: -0.1700

Data Index: 8143615 (Open Web Text)

Max Activating Token Index: 178

Text #15

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.7811. Min Act: -0.1700

Data Index: 647962 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8304. Min Act: -0.1700

Data Index: 390011 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.7623. Min Act: -0.1700

Data Index: 1979125 (Open Web Text)

Max Activating Token Index: 637

Text #18

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8030. Min Act: -0.1700

Data Index: 4097717 (Open Web Text)

Max Activating Token Index: 118

Text #19

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.7345. Min Act: -0.1700

Data Index: 4448245 (Open Web Text)

Max Activating Token Index: 816