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

Dataset: Open Web Text

Neuron 1659 in Layer 4

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: 4.9505. Min Range: -4.9505

Max Act: 4.9444. Min Act: -0.1700

Data Index: 7832326 (Open Web Text)

Max Activating Token Index: 691

Text #1

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.9312. Min Act: -0.1700

Data Index: 5407699 (Open Web Text)

Max Activating Token Index: 620

Text #2

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.9505. Min Act: -0.1700

Data Index: 4839825 (Open Web Text)

Max Activating Token Index: 144

Text #3

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8771. Min Act: -0.1700

Data Index: 8654083 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8822. Min Act: -0.1700

Data Index: 5164578 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.9083. Min Act: -0.1700

Data Index: 4766849 (Open Web Text)

Max Activating Token Index: 660

Text #6

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.9120. Min Act: -0.1700

Data Index: 1745295 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8920. Min Act: -0.1700

Data Index: 4745578 (Open Web Text)

Max Activating Token Index: 319

Text #8

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8924. Min Act: -0.1700

Data Index: 5012368 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8507. Min Act: -0.1700

Data Index: 513356 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8609. Min Act: -0.1700

Data Index: 4289179 (Open Web Text)

Max Activating Token Index: 880

Text #11

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8863. Min Act: -0.1700

Data Index: 3386870 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8681. Min Act: -0.1700

Data Index: 8212114 (Open Web Text)

Max Activating Token Index: 702

Text #13

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8094. Min Act: -0.1700

Data Index: 6755367 (Open Web Text)

Max Activating Token Index: 498

Text #14

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8274. Min Act: -0.1700

Data Index: 4899819 (Open Web Text)

Max Activating Token Index: 257

Text #15

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8302. Min Act: -0.1700

Data Index: 2805805 (Open Web Text)

Max Activating Token Index: 1006

Text #16

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8370. Min Act: -0.1700

Data Index: 4061826 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8170. Min Act: -0.1700

Data Index: 10001 (Open Web Text)

Max Activating Token Index: 168

Text #18

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8574. Min Act: -0.1700

Data Index: 3170324 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 4.9505. Min Range: -4.9505

Max Act: 4.8076. Min Act: -0.1700

Data Index: 5936035 (Open Web Text)

Max Activating Token Index: 344