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

Dataset: Open Web Text

Neuron 2365 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: 3.2295. Min Range: -3.2295

Max Act: 3.2295. Min Act: -0.1700

Data Index: 2050528 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 3.2295. Min Range: -3.2295

Max Act: 3.2070. Min Act: -0.1700

Data Index: 4753756 (Open Web Text)

Max Activating Token Index: 173

Text #2

Max Range: 3.2295. Min Range: -3.2295

Max Act: 3.1134. Min Act: -0.1700

Data Index: 6728960 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.2295. Min Range: -3.2295

Max Act: 3.0407. Min Act: -0.1700

Data Index: 8771584 (Open Web Text)

Max Activating Token Index: 159

Text #4

Max Range: 3.2295. Min Range: -3.2295

Max Act: 3.0258. Min Act: -0.1700

Data Index: 326312 (Open Web Text)

Max Activating Token Index: 824

Text #5

Max Range: 3.2295. Min Range: -3.2295

Max Act: 3.0367. Min Act: -0.1700

Data Index: 800972 (Open Web Text)

Max Activating Token Index: 991

Text #6

Max Range: 3.2295. Min Range: -3.2295

Max Act: 3.0040. Min Act: -0.1700

Data Index: 1873662 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.9952. Min Act: -0.1700

Data Index: 7356446 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.9271. Min Act: -0.1700

Data Index: 1238157 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.9657. Min Act: -0.1700

Data Index: 4063495 (Open Web Text)

Max Activating Token Index: 358

Text #10

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8936. Min Act: -0.1700

Data Index: 1568537 (Open Web Text)

Max Activating Token Index: 994

Text #11

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.9047. Min Act: -0.1700

Data Index: 4489346 (Open Web Text)

Max Activating Token Index: 385

Text #12

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8949. Min Act: -0.1700

Data Index: 7776793 (Open Web Text)

Max Activating Token Index: 42

Text #13

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8535. Min Act: -0.1700

Data Index: 5453991 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8444. Min Act: -0.1700

Data Index: 1101781 (Open Web Text)

Max Activating Token Index: 657

Text #15

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8116. Min Act: -0.1700

Data Index: 2055252 (Open Web Text)

Max Activating Token Index: 597

Text #16

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8044. Min Act: -0.1700

Data Index: 8222554 (Open Web Text)

Max Activating Token Index: 997

Text #17

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8042. Min Act: -0.1700

Data Index: 4437146 (Open Web Text)

Max Activating Token Index: 357

Text #18

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8048. Min Act: -0.1700

Data Index: 149549 (Open Web Text)

Max Activating Token Index: 951

Text #19

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.7657. Min Act: -0.1700

Data Index: 4082399 (Open Web Text)

Max Activating Token Index: 65