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

Dataset: Open Web Text

Neuron 2213 in Layer 6

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: 3.3616. Min Range: -3.3616

Max Act: 3.3616. Min Act: -0.1700

Data Index: 1615197 (Open Web Text)

Max Activating Token Index: 553

Text #1

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.3402. Min Act: -0.1700

Data Index: 8354369 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.3166. Min Act: -0.1700

Data Index: 1474985 (Open Web Text)

Max Activating Token Index: 236

Text #3

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.3176. Min Act: -0.1700

Data Index: 1696444 (Open Web Text)

Max Activating Token Index: 950

Text #4

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2927. Min Act: -0.1700

Data Index: 2936923 (Open Web Text)

Max Activating Token Index: 922

Text #5

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2673. Min Act: -0.1700

Data Index: 2397041 (Open Web Text)

Max Activating Token Index: 891

Text #6

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2429. Min Act: -0.1700

Data Index: 7711240 (Open Web Text)

Max Activating Token Index: 266

Text #7

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1799. Min Act: -0.1700

Data Index: 1196079 (Open Web Text)

Max Activating Token Index: 742

Text #8

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1501. Min Act: -0.1700

Data Index: 1028055 (Open Web Text)

Max Activating Token Index: 675

Text #9

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1511. Min Act: -0.1700

Data Index: 4195507 (Open Web Text)

Max Activating Token Index: 1011

Text #10

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1050. Min Act: -0.1700

Data Index: 3332991 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1454. Min Act: -0.1700

Data Index: 3031472 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1118. Min Act: -0.1700

Data Index: 8648217 (Open Web Text)

Max Activating Token Index: 770

Text #13

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1012. Min Act: -0.1700

Data Index: 1853889 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1118. Min Act: -0.1700

Data Index: 7356003 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.0836. Min Act: -0.1700

Data Index: 3271953 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.0631. Min Act: -0.1700

Data Index: 5486296 (Open Web Text)

Max Activating Token Index: 906

Text #17

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.0890. Min Act: -0.1700

Data Index: 1326167 (Open Web Text)

Max Activating Token Index: 466

Text #18

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.0897. Min Act: -0.1700

Data Index: 2618049 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.0798. Min Act: -0.1700

Data Index: 2471544 (Open Web Text)

Max Activating Token Index: 681