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

Dataset: Open Web Text

Neuron 2899 in Layer 0

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: 2.4538. Min Range: -2.4538

Max Act: 2.4538. Min Act: -0.1700

Data Index: 3944800 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.4429. Min Act: -0.1700

Data Index: 1693037 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.4057. Min Act: -0.1700

Data Index: 2320372 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3857. Min Act: -0.1700

Data Index: 5663610 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3961. Min Act: -0.1700

Data Index: 6089113 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3879. Min Act: -0.1700

Data Index: 6261619 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3834. Min Act: -0.1700

Data Index: 2247579 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3694. Min Act: -0.1700

Data Index: 8325749 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3680. Min Act: -0.1700

Data Index: 6643859 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3732. Min Act: -0.1700

Data Index: 6318558 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3793. Min Act: -0.1700

Data Index: 1822075 (Open Web Text)

Max Activating Token Index: 118

Text #11

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3752. Min Act: -0.1700

Data Index: 8478994 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3830. Min Act: -0.1700

Data Index: 3407194 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3591. Min Act: -0.1700

Data Index: 4003827 (Open Web Text)

Max Activating Token Index: 363

Text #14

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3616. Min Act: -0.1700

Data Index: 146428 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3550. Min Act: -0.1700

Data Index: 3510335 (Open Web Text)

Max Activating Token Index: 819

Text #16

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3543. Min Act: -0.1700

Data Index: 6320846 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3552. Min Act: -0.1700

Data Index: 2285425 (Open Web Text)

Max Activating Token Index: 116

Text #18

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3541. Min Act: -0.1700

Data Index: 4380082 (Open Web Text)

Max Activating Token Index: 425

Text #19

Max Range: 2.4538. Min Range: -2.4538

Max Act: 2.3548. Min Act: -0.1700

Data Index: 5059018 (Open Web Text)

Max Activating Token Index: 16