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

Dataset: Open Web Text

Neuron 2839 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: 4.1580. Min Range: -4.1580

Max Act: 4.1580. Min Act: -0.1700

Data Index: 105711 (Open Web Text)

Max Activating Token Index: 240

Text #1

Max Range: 4.1580. Min Range: -4.1580

Max Act: 4.0565. Min Act: -0.1700

Data Index: 8596276 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 4.1580. Min Range: -4.1580

Max Act: 4.0589. Min Act: -0.1700

Data Index: 5051289 (Open Web Text)

Max Activating Token Index: 93

Text #3

Max Range: 4.1580. Min Range: -4.1580

Max Act: 4.0059. Min Act: -0.1700

Data Index: 4802402 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 4.1580. Min Range: -4.1580

Max Act: 4.0349. Min Act: -0.1700

Data Index: 6381860 (Open Web Text)

Max Activating Token Index: 451

Text #5

Max Range: 4.1580. Min Range: -4.1580

Max Act: 4.0091. Min Act: -0.1700

Data Index: 8429815 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 4.1580. Min Range: -4.1580

Max Act: 4.0080. Min Act: -0.1700

Data Index: 6381874 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 4.1580. Min Range: -4.1580

Max Act: 4.0053. Min Act: -0.1700

Data Index: 8090464 (Open Web Text)

Max Activating Token Index: 341

Text #8

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.9508. Min Act: -0.1700

Data Index: 2832508 (Open Web Text)

Max Activating Token Index: 278

Text #9

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.9378. Min Act: -0.1700

Data Index: 8456089 (Open Web Text)

Max Activating Token Index: 663

Text #10

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8773. Min Act: -0.1700

Data Index: 7418060 (Open Web Text)

Max Activating Token Index: 802

Text #11

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8753. Min Act: -0.1700

Data Index: 280471 (Open Web Text)

Max Activating Token Index: 848

Text #12

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.9044. Min Act: -0.1700

Data Index: 4028886 (Open Web Text)

Max Activating Token Index: 881

Text #13

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8810. Min Act: -0.1700

Data Index: 6467139 (Open Web Text)

Max Activating Token Index: 117

Text #14

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8839. Min Act: -0.1700

Data Index: 7418059 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8805. Min Act: -0.1700

Data Index: 4842548 (Open Web Text)

Max Activating Token Index: 818

Text #16

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8478. Min Act: -0.1700

Data Index: 1927214 (Open Web Text)

Max Activating Token Index: 665

Text #17

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8224. Min Act: -0.1700

Data Index: 4260085 (Open Web Text)

Max Activating Token Index: 956

Text #18

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8307. Min Act: -0.1700

Data Index: 3629106 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 4.1580. Min Range: -4.1580

Max Act: 3.8293. Min Act: -0.1700

Data Index: 6702943 (Open Web Text)

Max Activating Token Index: 638