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

Dataset: Open Web Text

Neuron 615 in Layer 5

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: 5.0058. Min Range: -5.0058

Max Act: 5.0058. Min Act: -0.1700

Data Index: 5914400 (Open Web Text)

Max Activating Token Index: 113

Text #1

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.8982. Min Act: -0.1700

Data Index: 6817247 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.9019. Min Act: -0.1700

Data Index: 4990461 (Open Web Text)

Max Activating Token Index: 254

Text #3

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.8274. Min Act: -0.1700

Data Index: 2923348 (Open Web Text)

Max Activating Token Index: 598

Text #4

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.8437. Min Act: -0.1700

Data Index: 3211584 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.7710. Min Act: -0.1700

Data Index: 3822545 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.7531. Min Act: -0.1700

Data Index: 8691288 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.7274. Min Act: -0.1700

Data Index: 8302212 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.7322. Min Act: -0.1700

Data Index: 597900 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6782. Min Act: -0.1700

Data Index: 8598352 (Open Web Text)

Max Activating Token Index: 655

Text #10

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6976. Min Act: -0.1700

Data Index: 7144307 (Open Web Text)

Max Activating Token Index: 435

Text #11

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6660. Min Act: -0.1700

Data Index: 7595978 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.7011. Min Act: -0.1700

Data Index: 1924590 (Open Web Text)

Max Activating Token Index: 736

Text #13

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6652. Min Act: -0.1700

Data Index: 1109280 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6578. Min Act: -0.1700

Data Index: 1062792 (Open Web Text)

Max Activating Token Index: 484

Text #15

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6365. Min Act: -0.1700

Data Index: 489096 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6266. Min Act: -0.1700

Data Index: 5368679 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6471. Min Act: -0.1700

Data Index: 7378724 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.6548. Min Act: -0.1700

Data Index: 2103562 (Open Web Text)

Max Activating Token Index: 538

Text #19

Max Range: 5.0058. Min Range: -5.0058

Max Act: 4.5857. Min Act: -0.1700

Data Index: 6430635 (Open Web Text)

Max Activating Token Index: 1014