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

Dataset: Open Web Text

Neuron 1539 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: 5.0044. Min Range: -5.0044

Max Act: 5.0044. Min Act: -0.1700

Data Index: 8012742 (Open Web Text)

Max Activating Token Index: 731

Text #1

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.8332. Min Act: -0.1700

Data Index: 5132129 (Open Web Text)

Max Activating Token Index: 387

Text #2

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.8132. Min Act: -0.1700

Data Index: 7968892 (Open Web Text)

Max Activating Token Index: 1012

Text #3

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.7325. Min Act: -0.1700

Data Index: 7507212 (Open Web Text)

Max Activating Token Index: 184

Text #4

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.7889. Min Act: -0.1700

Data Index: 3325570 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.7113. Min Act: -0.1700

Data Index: 2052731 (Open Web Text)

Max Activating Token Index: 415

Text #6

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.7435. Min Act: -0.1700

Data Index: 123417 (Open Web Text)

Max Activating Token Index: 444

Text #7

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.7454. Min Act: -0.1700

Data Index: 2013061 (Open Web Text)

Max Activating Token Index: 721

Text #8

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.7400. Min Act: -0.1700

Data Index: 6353807 (Open Web Text)

Max Activating Token Index: 463

Text #9

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.6768. Min Act: -0.1700

Data Index: 5564724 (Open Web Text)

Max Activating Token Index: 370

Text #10

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.6770. Min Act: -0.1700

Data Index: 6296122 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.6730. Min Act: -0.1700

Data Index: 5589729 (Open Web Text)

Max Activating Token Index: 869

Text #12

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.6046. Min Act: -0.1700

Data Index: 5922368 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.6279. Min Act: -0.1700

Data Index: 1325461 (Open Web Text)

Max Activating Token Index: 727

Text #14

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.6264. Min Act: -0.1700

Data Index: 3534178 (Open Web Text)

Max Activating Token Index: 978

Text #15

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.6113. Min Act: -0.1700

Data Index: 49867 (Open Web Text)

Max Activating Token Index: 298

Text #16

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.5550. Min Act: -0.1700

Data Index: 1737807 (Open Web Text)

Max Activating Token Index: 277

Text #17

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.5853. Min Act: -0.1700

Data Index: 1975317 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.5534. Min Act: -0.1700

Data Index: 765817 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 5.0044. Min Range: -5.0044

Max Act: 4.5965. Min Act: -0.1700

Data Index: 1184920 (Open Web Text)

Max Activating Token Index: 840