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

Dataset: Open Web Text

Neuron 249 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: 1.8688. Min Range: -1.8688

Max Act: 1.8688. Min Act: -0.1700

Data Index: 2738474 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8639. Min Act: -0.1700

Data Index: 7203163 (Open Web Text)

Max Activating Token Index: 455

Text #2

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8375. Min Act: -0.1700

Data Index: 1316288 (Open Web Text)

Max Activating Token Index: 650

Text #3

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8153. Min Act: -0.1700

Data Index: 915570 (Open Web Text)

Max Activating Token Index: 175

Text #4

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8260. Min Act: -0.1700

Data Index: 7764102 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8069. Min Act: -0.1700

Data Index: 8555583 (Open Web Text)

Max Activating Token Index: 918

Text #6

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8057. Min Act: -0.1684

Data Index: 7005751 (Open Web Text)

Max Activating Token Index: 329

Text #7

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8057. Min Act: -0.1693

Data Index: 7005739 (Open Web Text)

Max Activating Token Index: 716

Text #8

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7923. Min Act: -0.1700

Data Index: 17570 (Open Web Text)

Max Activating Token Index: 406

Text #9

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7824. Min Act: -0.1700

Data Index: 413130 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7853. Min Act: -0.1700

Data Index: 6962535 (Open Web Text)

Max Activating Token Index: 223

Text #11

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7845. Min Act: -0.1688

Data Index: 373466 (Open Web Text)

Max Activating Token Index: 261

Text #12

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7653. Min Act: -0.1700

Data Index: 373452 (Open Web Text)

Max Activating Token Index: 776

Text #13

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7712. Min Act: -0.1700

Data Index: 6700219 (Open Web Text)

Max Activating Token Index: 76

Text #14

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7814. Min Act: -0.1700

Data Index: 4644159 (Open Web Text)

Max Activating Token Index: 894

Text #15

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7830. Min Act: -0.1663

Data Index: 8484862 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7560. Min Act: -0.1700

Data Index: 6916883 (Open Web Text)

Max Activating Token Index: 89

Text #17

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7670. Min Act: -0.1700

Data Index: 3378104 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7400. Min Act: -0.1700

Data Index: 4468145 (Open Web Text)

Max Activating Token Index: 963

Text #19

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7439. Min Act: -0.1637

Data Index: 1090030 (Open Web Text)

Max Activating Token Index: 984