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

Dataset: Open Web Text

Neuron 1536 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: 3.1746. Min Range: -3.1746

Max Act: 3.1746. Min Act: -0.1700

Data Index: 3990382 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1700. Min Act: -0.1700

Data Index: 2161327 (Open Web Text)

Max Activating Token Index: 520

Text #2

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1426. Min Act: -0.1700

Data Index: 3102074 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1312. Min Act: -0.1700

Data Index: 4789064 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1141. Min Act: -0.1700

Data Index: 6371786 (Open Web Text)

Max Activating Token Index: 338

Text #5

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0911. Min Act: -0.1700

Data Index: 168202 (Open Web Text)

Max Activating Token Index: 894

Text #6

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0998. Min Act: -0.1700

Data Index: 973001 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1004. Min Act: -0.1700

Data Index: 2658372 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0749. Min Act: -0.1700

Data Index: 7693605 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0771. Min Act: -0.1700

Data Index: 6371796 (Open Web Text)

Max Activating Token Index: 304

Text #10

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0583. Min Act: -0.1700

Data Index: 2508646 (Open Web Text)

Max Activating Token Index: 691

Text #11

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0588. Min Act: -0.1700

Data Index: 7053963 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0664. Min Act: -0.1700

Data Index: 4127065 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0586. Min Act: -0.1700

Data Index: 363697 (Open Web Text)

Max Activating Token Index: 322

Text #14

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0393. Min Act: -0.1700

Data Index: 2299845 (Open Web Text)

Max Activating Token Index: 860

Text #15

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0333. Min Act: -0.1700

Data Index: 8367835 (Open Web Text)

Max Activating Token Index: 805

Text #16

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0281. Min Act: -0.1700

Data Index: 2562836 (Open Web Text)

Max Activating Token Index: 552

Text #17

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0130. Min Act: -0.1700

Data Index: 6676103 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0114. Min Act: -0.1700

Data Index: 2738163 (Open Web Text)

Max Activating Token Index: 814

Text #19

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0244. Min Act: -0.1700

Data Index: 6987780 (Open Web Text)

Max Activating Token Index: 814