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

Dataset: Open Web Text

Neuron 229 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: 4.3563. Min Range: -4.3563

Max Act: 4.3563. Min Act: -0.1700

Data Index: 5734452 (Open Web Text)

Max Activating Token Index: 273

Text #1

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.1268. Min Act: -0.1700

Data Index: 5563285 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0495. Min Act: -0.1700

Data Index: 2811992 (Open Web Text)

Max Activating Token Index: 328

Text #3

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0604. Min Act: -0.1700

Data Index: 6587584 (Open Web Text)

Max Activating Token Index: 675

Text #4

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0822. Min Act: -0.1700

Data Index: 3325302 (Open Web Text)

Max Activating Token Index: 641

Text #5

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0486. Min Act: -0.1700

Data Index: 973787 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0278. Min Act: -0.1700

Data Index: 8749510 (Open Web Text)

Max Activating Token Index: 979

Text #7

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0413. Min Act: -0.1700

Data Index: 7153209 (Open Web Text)

Max Activating Token Index: 34

Text #8

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0284. Min Act: -0.1700

Data Index: 4291789 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0292. Min Act: -0.1700

Data Index: 8288033 (Open Web Text)

Max Activating Token Index: 784

Text #10

Max Range: 4.3563. Min Range: -4.3563

Max Act: 4.0104. Min Act: -0.1700

Data Index: 4377942 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9861. Min Act: -0.1700

Data Index: 7759860 (Open Web Text)

Max Activating Token Index: 276

Text #12

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9861. Min Act: -0.1700

Data Index: 6150920 (Open Web Text)

Max Activating Token Index: 682

Text #13

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9906. Min Act: -0.1700

Data Index: 8463693 (Open Web Text)

Max Activating Token Index: 779

Text #14

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9817. Min Act: -0.1700

Data Index: 6619245 (Open Web Text)

Max Activating Token Index: 859

Text #15

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9966. Min Act: -0.1700

Data Index: 8473156 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9976. Min Act: -0.1700

Data Index: 7103038 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9929. Min Act: -0.1700

Data Index: 2606668 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9525. Min Act: -0.1700

Data Index: 62307 (Open Web Text)

Max Activating Token Index: 136

Text #19

Max Range: 4.3563. Min Range: -4.3563

Max Act: 3.9506. Min Act: -0.1700

Data Index: 2807098 (Open Web Text)

Max Activating Token Index: 636