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

Dataset: Open Web Text

Neuron 651 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: 4.2361. Min Range: -4.2361

Max Act: 4.2361. Min Act: -0.1700

Data Index: 1270180 (Open Web Text)

Max Activating Token Index: 645

Text #1

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.2054. Min Act: -0.1700

Data Index: 711622 (Open Web Text)

Max Activating Token Index: 916

Text #2

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.1628. Min Act: -0.1700

Data Index: 4071781 (Open Web Text)

Max Activating Token Index: 265

Text #3

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.1578. Min Act: -0.1700

Data Index: 4399516 (Open Web Text)

Max Activating Token Index: 851

Text #4

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.1501. Min Act: -0.1700

Data Index: 4032428 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.1118. Min Act: -0.1700

Data Index: 1976462 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.1165. Min Act: -0.1700

Data Index: 5604962 (Open Web Text)

Max Activating Token Index: 893

Text #7

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.1114. Min Act: -0.1700

Data Index: 3678425 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.1049. Min Act: -0.1700

Data Index: 2443344 (Open Web Text)

Max Activating Token Index: 980

Text #9

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.1226. Min Act: -0.1700

Data Index: 92640 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0771. Min Act: -0.1700

Data Index: 1493872 (Open Web Text)

Max Activating Token Index: 436

Text #11

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0680. Min Act: -0.1700

Data Index: 1336416 (Open Web Text)

Max Activating Token Index: 216

Text #12

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0623. Min Act: -0.1700

Data Index: 1041992 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0914. Min Act: -0.1700

Data Index: 4337126 (Open Web Text)

Max Activating Token Index: 704

Text #14

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0400. Min Act: -0.1700

Data Index: 2631062 (Open Web Text)

Max Activating Token Index: 310

Text #15

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0585. Min Act: -0.1700

Data Index: 1036437 (Open Web Text)

Max Activating Token Index: 802

Text #16

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0498. Min Act: -0.1700

Data Index: 4071780 (Open Web Text)

Max Activating Token Index: 784

Text #17

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0234. Min Act: -0.1700

Data Index: 794107 (Open Web Text)

Max Activating Token Index: 301

Text #18

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0334. Min Act: -0.1700

Data Index: 2870063 (Open Web Text)

Max Activating Token Index: 926

Text #19

Max Range: 4.2361. Min Range: -4.2361

Max Act: 4.0208. Min Act: -0.1700

Data Index: 2566081 (Open Web Text)

Max Activating Token Index: 612