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

Dataset: Open Web Text

Neuron 1828 in Layer 5

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: 4.1991. Min Range: -4.1991

Max Act: 4.1991. Min Act: -0.1700

Data Index: 415829 (Open Web Text)

Max Activating Token Index: 337

Text #1

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1864. Min Act: -0.1700

Data Index: 5215005 (Open Web Text)

Max Activating Token Index: 984

Text #2

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1709. Min Act: -0.1700

Data Index: 1136902 (Open Web Text)

Max Activating Token Index: 836

Text #3

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1511. Min Act: -0.1700

Data Index: 6199134 (Open Web Text)

Max Activating Token Index: 104

Text #4

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1515. Min Act: -0.1700

Data Index: 8427739 (Open Web Text)

Max Activating Token Index: 741

Text #5

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1526. Min Act: -0.1700

Data Index: 1384698 (Open Web Text)

Max Activating Token Index: 306

Text #6

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1620. Min Act: -0.1700

Data Index: 1972754 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1048. Min Act: -0.1700

Data Index: 395990 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1456. Min Act: -0.1700

Data Index: 5421381 (Open Web Text)

Max Activating Token Index: 362

Text #9

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1153. Min Act: -0.1700

Data Index: 2553298 (Open Web Text)

Max Activating Token Index: 259

Text #10

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1427. Min Act: -0.1700

Data Index: 2426342 (Open Web Text)

Max Activating Token Index: 348

Text #11

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1473. Min Act: -0.1700

Data Index: 806307 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1140. Min Act: -0.1700

Data Index: 5196516 (Open Web Text)

Max Activating Token Index: 369

Text #13

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1114. Min Act: -0.1700

Data Index: 918980 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1102. Min Act: -0.1700

Data Index: 7676849 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1179. Min Act: -0.1700

Data Index: 7695326 (Open Web Text)

Max Activating Token Index: 109

Text #16

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1091. Min Act: -0.1700

Data Index: 3264607 (Open Web Text)

Max Activating Token Index: 360

Text #17

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1195. Min Act: -0.1700

Data Index: 8074820 (Open Web Text)

Max Activating Token Index: 234

Text #18

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1009. Min Act: -0.1700

Data Index: 3539200 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.1991. Min Range: -4.1991

Max Act: 4.1053. Min Act: -0.1700

Data Index: 3648070 (Open Web Text)

Max Activating Token Index: 44