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

Dataset: Open Web Text

Neuron 1033 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: 3.5334. Min Range: -3.5334

Max Act: 3.5334. Min Act: -0.1700

Data Index: 3882235 (Open Web Text)

Max Activating Token Index: 49

Text #1

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.5285. Min Act: -0.1700

Data Index: 7130842 (Open Web Text)

Max Activating Token Index: 327

Text #2

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.5032. Min Act: -0.1700

Data Index: 4383457 (Open Web Text)

Max Activating Token Index: 649

Text #3

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.5217. Min Act: -0.1700

Data Index: 8643859 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4514. Min Act: -0.1700

Data Index: 5393003 (Open Web Text)

Max Activating Token Index: 884

Text #5

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4700. Min Act: -0.1700

Data Index: 8469864 (Open Web Text)

Max Activating Token Index: 905

Text #6

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4465. Min Act: -0.1700

Data Index: 1118147 (Open Web Text)

Max Activating Token Index: 842

Text #7

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4928. Min Act: -0.1700

Data Index: 6232726 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4483. Min Act: -0.1700

Data Index: 6747508 (Open Web Text)

Max Activating Token Index: 623

Text #9

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.3972. Min Act: -0.1700

Data Index: 3908657 (Open Web Text)

Max Activating Token Index: 863

Text #10

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4400. Min Act: -0.1700

Data Index: 6518250 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4199. Min Act: -0.1700

Data Index: 1263597 (Open Web Text)

Max Activating Token Index: 444

Text #12

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4074. Min Act: -0.1700

Data Index: 8543963 (Open Web Text)

Max Activating Token Index: 687

Text #13

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4236. Min Act: -0.1700

Data Index: 263699 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4153. Min Act: -0.1700

Data Index: 8695558 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4159. Min Act: -0.1700

Data Index: 1610117 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.3966. Min Act: -0.1700

Data Index: 6686947 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4048. Min Act: -0.1700

Data Index: 7587888 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.3919. Min Act: -0.1700

Data Index: 4815553 (Open Web Text)

Max Activating Token Index: 856

Text #19

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4256. Min Act: -0.1700

Data Index: 8684633 (Open Web Text)

Max Activating Token Index: 542