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

Dataset: Open Web Text

Neuron 1841 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: 4.3112. Min Range: -4.3112

Max Act: 4.3112. Min Act: -0.1700

Data Index: 4279761 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.1806. Min Act: -0.1700

Data Index: 4108643 (Open Web Text)

Max Activating Token Index: 981

Text #2

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.1845. Min Act: -0.1700

Data Index: 1888968 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.1091. Min Act: -0.1700

Data Index: 7740111 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.0854. Min Act: -0.1700

Data Index: 3698272 (Open Web Text)

Max Activating Token Index: 896

Text #5

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.0559. Min Act: -0.1700

Data Index: 428279 (Open Web Text)

Max Activating Token Index: 934

Text #6

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.0051. Min Act: -0.1700

Data Index: 7516070 (Open Web Text)

Max Activating Token Index: 791

Text #7

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9660. Min Act: -0.1700

Data Index: 2895239 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9808. Min Act: -0.1700

Data Index: 5813547 (Open Web Text)

Max Activating Token Index: 616

Text #9

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9838. Min Act: -0.1700

Data Index: 1236894 (Open Web Text)

Max Activating Token Index: 379

Text #10

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9121. Min Act: -0.1700

Data Index: 4496946 (Open Web Text)

Max Activating Token Index: 691

Text #11

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9397. Min Act: -0.1700

Data Index: 2643454 (Open Web Text)

Max Activating Token Index: 867

Text #12

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9521. Min Act: -0.1700

Data Index: 4795176 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9360. Min Act: -0.1700

Data Index: 2350604 (Open Web Text)

Max Activating Token Index: 353

Text #14

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9691. Min Act: -0.1700

Data Index: 7951708 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9490. Min Act: -0.1700

Data Index: 7084324 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9149. Min Act: -0.1700

Data Index: 4195451 (Open Web Text)

Max Activating Token Index: 617

Text #17

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9085. Min Act: -0.1700

Data Index: 4614786 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9122. Min Act: -0.1700

Data Index: 4959859 (Open Web Text)

Max Activating Token Index: 830

Text #19

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.9180. Min Act: -0.1700

Data Index: 5544309 (Open Web Text)

Max Activating Token Index: 948