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

Dataset: Open Web Text

Neuron 661 in Layer 2

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: 1.9695. Min Range: -1.9695

Max Act: 1.9691. Min Act: -0.1699

Data Index: 4500279 (Open Web Text)

Max Activating Token Index: 926

Text #1

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.9695. Min Act: -0.1700

Data Index: 4844819 (Open Web Text)

Max Activating Token Index: 995

Text #2

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.9330. Min Act: -0.1700

Data Index: 4808620 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.9078. Min Act: -0.1700

Data Index: 6981139 (Open Web Text)

Max Activating Token Index: 175

Text #4

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.9120. Min Act: -0.1700

Data Index: 6904943 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.9039. Min Act: -0.1699

Data Index: 5680361 (Open Web Text)

Max Activating Token Index: 431

Text #6

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.9022. Min Act: -0.1700

Data Index: 2189602 (Open Web Text)

Max Activating Token Index: 375

Text #7

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8966. Min Act: -0.1700

Data Index: 4339431 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8959. Min Act: -0.1700

Data Index: 7996550 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8826. Min Act: -0.1700

Data Index: 1741863 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8798. Min Act: -0.1694

Data Index: 521568 (Open Web Text)

Max Activating Token Index: 174

Text #11

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8930. Min Act: -0.1700

Data Index: 1276363 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8807. Min Act: -0.1700

Data Index: 1510279 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8784. Min Act: -0.1700

Data Index: 2990653 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8796. Min Act: -0.1699

Data Index: 6743706 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8803. Min Act: -0.1700

Data Index: 5710706 (Open Web Text)

Max Activating Token Index: 627

Text #16

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8785. Min Act: -0.1700

Data Index: 4373989 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8643. Min Act: -0.1700

Data Index: 5505588 (Open Web Text)

Max Activating Token Index: 495

Text #18

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8726. Min Act: -0.1700

Data Index: 226405 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8585. Min Act: -0.1700

Data Index: 2909232 (Open Web Text)

Max Activating Token Index: 933