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

Dataset: Open Web Text

Neuron 2658 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: 6.1610. Min Range: -6.1610

Max Act: 6.1610. Min Act: -0.1700

Data Index: 781394 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 6.1610. Min Range: -6.1610

Max Act: 6.1089. Min Act: -0.1700

Data Index: 4975908 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 6.1610. Min Range: -6.1610

Max Act: 6.0634. Min Act: -0.1700

Data Index: 5239345 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.9892. Min Act: -0.1700

Data Index: 963258 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.9465. Min Act: -0.1700

Data Index: 6755729 (Open Web Text)

Max Activating Token Index: 794

Text #5

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.9504. Min Act: -0.1700

Data Index: 4058526 (Open Web Text)

Max Activating Token Index: 863

Text #6

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.9376. Min Act: -0.1700

Data Index: 926819 (Open Web Text)

Max Activating Token Index: 803

Text #7

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.9296. Min Act: -0.1700

Data Index: 2891271 (Open Web Text)

Max Activating Token Index: 547

Text #8

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8728. Min Act: -0.1700

Data Index: 4409123 (Open Web Text)

Max Activating Token Index: 277

Text #9

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8916. Min Act: -0.1700

Data Index: 5513535 (Open Web Text)

Max Activating Token Index: 775

Text #10

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8852. Min Act: -0.1700

Data Index: 4469481 (Open Web Text)

Max Activating Token Index: 806

Text #11

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8734. Min Act: -0.1700

Data Index: 8312641 (Open Web Text)

Max Activating Token Index: 711

Text #12

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8741. Min Act: -0.1700

Data Index: 5233893 (Open Web Text)

Max Activating Token Index: 947

Text #13

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8447. Min Act: -0.1700

Data Index: 1018242 (Open Web Text)

Max Activating Token Index: 931

Text #14

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8105. Min Act: -0.1700

Data Index: 4034846 (Open Web Text)

Max Activating Token Index: 222

Text #15

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8626. Min Act: -0.1700

Data Index: 2016702 (Open Web Text)

Max Activating Token Index: 621

Text #16

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8619. Min Act: -0.1700

Data Index: 672730 (Open Web Text)

Max Activating Token Index: 301

Text #17

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8525. Min Act: -0.1700

Data Index: 6666990 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.8777. Min Act: -0.1700

Data Index: 4868939 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 6.1610. Min Range: -6.1610

Max Act: 5.7906. Min Act: -0.1700

Data Index: 2659609 (Open Web Text)

Max Activating Token Index: 640