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

Dataset: Open Web Text

Neuron 2030 in Layer 4

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: 4.1084. Min Range: -4.1084

Max Act: 4.1084. Min Act: -0.1700

Data Index: 6259095 (Open Web Text)

Max Activating Token Index: 504

Text #1

Max Range: 4.1084. Min Range: -4.1084

Max Act: 4.0219. Min Act: -0.1700

Data Index: 8027137 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 4.1084. Min Range: -4.1084

Max Act: 4.0518. Min Act: -0.1700

Data Index: 4393729 (Open Web Text)

Max Activating Token Index: 752

Text #3

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.9804. Min Act: -0.1700

Data Index: 85673 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.8472. Min Act: -0.1700

Data Index: 6923034 (Open Web Text)

Max Activating Token Index: 172

Text #5

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7920. Min Act: -0.1700

Data Index: 7608699 (Open Web Text)

Max Activating Token Index: 383

Text #6

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.8050. Min Act: -0.1700

Data Index: 657716 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7827. Min Act: -0.1700

Data Index: 4002968 (Open Web Text)

Max Activating Token Index: 577

Text #8

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7824. Min Act: -0.1700

Data Index: 4892636 (Open Web Text)

Max Activating Token Index: 315

Text #9

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7386. Min Act: -0.1700

Data Index: 2378453 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7484. Min Act: -0.1700

Data Index: 7758601 (Open Web Text)

Max Activating Token Index: 194

Text #11

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7589. Min Act: -0.1700

Data Index: 2938142 (Open Web Text)

Max Activating Token Index: 931

Text #12

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7438. Min Act: -0.1700

Data Index: 1577488 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7333. Min Act: -0.1700

Data Index: 2809752 (Open Web Text)

Max Activating Token Index: 113

Text #14

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7358. Min Act: -0.1700

Data Index: 2089024 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.6954. Min Act: -0.1700

Data Index: 7797901 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7406. Min Act: -0.1700

Data Index: 694343 (Open Web Text)

Max Activating Token Index: 663

Text #17

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7357. Min Act: -0.1700

Data Index: 17958 (Open Web Text)

Max Activating Token Index: 773

Text #18

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.6822. Min Act: -0.1700

Data Index: 677903 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 4.1084. Min Range: -4.1084

Max Act: 3.7135. Min Act: -0.1700

Data Index: 6469951 (Open Web Text)

Max Activating Token Index: 306