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

Dataset: Open Web Text

Neuron 3042 in Layer 6

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: 4.0882. Min Range: -4.0882

Max Act: 4.0882. Min Act: -0.1700

Data Index: 7162622 (Open Web Text)

Max Activating Token Index: 335

Text #1

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0771. Min Act: -0.1700

Data Index: 8355774 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0582. Min Act: -0.1700

Data Index: 7588304 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0433. Min Act: -0.1700

Data Index: 8386714 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0335. Min Act: -0.1700

Data Index: 2287557 (Open Web Text)

Max Activating Token Index: 813

Text #5

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9827. Min Act: -0.1700

Data Index: 7883597 (Open Web Text)

Max Activating Token Index: 822

Text #6

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9702. Min Act: -0.1700

Data Index: 1494903 (Open Web Text)

Max Activating Token Index: 416

Text #7

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9579. Min Act: -0.1700

Data Index: 1741790 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9428. Min Act: -0.1700

Data Index: 8343590 (Open Web Text)

Max Activating Token Index: 1014

Text #9

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9746. Min Act: -0.1700

Data Index: 2287556 (Open Web Text)

Max Activating Token Index: 593

Text #10

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9612. Min Act: -0.1700

Data Index: 1235888 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9072. Min Act: -0.1700

Data Index: 1556215 (Open Web Text)

Max Activating Token Index: 861

Text #12

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9404. Min Act: -0.1700

Data Index: 3180014 (Open Web Text)

Max Activating Token Index: 909

Text #13

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9240. Min Act: -0.1700

Data Index: 1956457 (Open Web Text)

Max Activating Token Index: 747

Text #14

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9285. Min Act: -0.1700

Data Index: 2840544 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8887. Min Act: -0.1700

Data Index: 4221150 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8756. Min Act: -0.1700

Data Index: 6875735 (Open Web Text)

Max Activating Token Index: 1012

Text #17

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9302. Min Act: -0.1700

Data Index: 5183497 (Open Web Text)

Max Activating Token Index: 806

Text #18

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8817. Min Act: -0.1700

Data Index: 6833306 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8878. Min Act: -0.1700

Data Index: 129117 (Open Web Text)

Max Activating Token Index: 473