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

Dataset: Open Web Text

Neuron 2581 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: 4.8095. Min Range: -4.8095

Max Act: 4.8095. Min Act: -0.1700

Data Index: 1348125 (Open Web Text)

Max Activating Token Index: 362

Text #1

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7550. Min Act: -0.1700

Data Index: 6020646 (Open Web Text)

Max Activating Token Index: 384

Text #2

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7727. Min Act: -0.1700

Data Index: 72453 (Open Web Text)

Max Activating Token Index: 474

Text #3

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7420. Min Act: -0.1700

Data Index: 7414547 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7466. Min Act: -0.1700

Data Index: 1788413 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7302. Min Act: -0.1700

Data Index: 601864 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7565. Min Act: -0.1700

Data Index: 6791061 (Open Web Text)

Max Activating Token Index: 743

Text #7

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7217. Min Act: -0.1700

Data Index: 5639891 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.6904. Min Act: -0.1700

Data Index: 3433332 (Open Web Text)

Max Activating Token Index: 342

Text #9

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7028. Min Act: -0.1700

Data Index: 1475172 (Open Web Text)

Max Activating Token Index: 456

Text #10

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7255. Min Act: -0.1700

Data Index: 6849606 (Open Web Text)

Max Activating Token Index: 444

Text #11

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.7062. Min Act: -0.1700

Data Index: 4369833 (Open Web Text)

Max Activating Token Index: 958

Text #12

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.6467. Min Act: -0.1700

Data Index: 7754334 (Open Web Text)

Max Activating Token Index: 251

Text #13

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.6893. Min Act: -0.1700

Data Index: 8606057 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.6404. Min Act: -0.1700

Data Index: 4539162 (Open Web Text)

Max Activating Token Index: 391

Text #15

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.6526. Min Act: -0.1700

Data Index: 5135674 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.6776. Min Act: -0.1700

Data Index: 3759493 (Open Web Text)

Max Activating Token Index: 518

Text #17

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.6173. Min Act: -0.1700

Data Index: 2456458 (Open Web Text)

Max Activating Token Index: 698

Text #18

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.5975. Min Act: -0.1700

Data Index: 2953602 (Open Web Text)

Max Activating Token Index: 369

Text #19

Max Range: 4.8095. Min Range: -4.8095

Max Act: 4.6218. Min Act: -0.1700

Data Index: 3845913 (Open Web Text)

Max Activating Token Index: 447