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

Dataset: Open Web Text

Neuron 406 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: 4.8729. Min Range: -4.8729

Max Act: 4.8729. Min Act: -0.1700

Data Index: 3848637 (Open Web Text)

Max Activating Token Index: 744

Text #1

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.7612. Min Act: -0.1700

Data Index: 5007756 (Open Web Text)

Max Activating Token Index: 520

Text #2

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.7514. Min Act: -0.1700

Data Index: 7865820 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.6872. Min Act: -0.1700

Data Index: 7644578 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.6309. Min Act: -0.1700

Data Index: 7260492 (Open Web Text)

Max Activating Token Index: 593

Text #5

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.6552. Min Act: -0.1700

Data Index: 6163794 (Open Web Text)

Max Activating Token Index: 145

Text #6

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.6513. Min Act: -0.1700

Data Index: 8663195 (Open Web Text)

Max Activating Token Index: 278

Text #7

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5568. Min Act: -0.1700

Data Index: 7498141 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5924. Min Act: -0.1700

Data Index: 281067 (Open Web Text)

Max Activating Token Index: 445

Text #9

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.4927. Min Act: -0.1700

Data Index: 5670726 (Open Web Text)

Max Activating Token Index: 226

Text #10

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5864. Min Act: -0.1700

Data Index: 3828337 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5559. Min Act: -0.1700

Data Index: 5193580 (Open Web Text)

Max Activating Token Index: 36

Text #12

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5027. Min Act: -0.1700

Data Index: 8364644 (Open Web Text)

Max Activating Token Index: 32

Text #13

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5350. Min Act: -0.1700

Data Index: 6113053 (Open Web Text)

Max Activating Token Index: 729

Text #14

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.4771. Min Act: -0.1700

Data Index: 207197 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5208. Min Act: -0.1700

Data Index: 1117965 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5279. Min Act: -0.1700

Data Index: 5535578 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5330. Min Act: -0.1700

Data Index: 7201629 (Open Web Text)

Max Activating Token Index: 941

Text #18

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.5107. Min Act: -0.1700

Data Index: 5721037 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 4.8729. Min Range: -4.8729

Max Act: 4.4979. Min Act: -0.1700

Data Index: 7498131 (Open Web Text)

Max Activating Token Index: 99