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

Dataset: Open Web Text

Neuron 2582 in Layer 1

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: 1.6358. Min Range: -1.6358

Max Act: 1.6358. Min Act: -0.1672

Data Index: 8694879 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5844. Min Act: -0.1700

Data Index: 1813135 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5827. Min Act: -0.1698

Data Index: 2456884 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5708. Min Act: -0.1698

Data Index: 370555 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5691. Min Act: -0.1700

Data Index: 2327724 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5610. Min Act: -0.1693

Data Index: 8299874 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5654. Min Act: -0.1700

Data Index: 7988108 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5520. Min Act: -0.1700

Data Index: 2915816 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5258. Min Act: -0.1698

Data Index: 7481813 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5341. Min Act: -0.1699

Data Index: 6922153 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5338. Min Act: -0.1700

Data Index: 3693950 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5211. Min Act: -0.1700

Data Index: 4971671 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5302. Min Act: -0.1697

Data Index: 2686799 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5244. Min Act: -0.1700

Data Index: 5721901 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5170. Min Act: -0.1700

Data Index: 1754582 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5171. Min Act: -0.1700

Data Index: 254480 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5163. Min Act: -0.1700

Data Index: 4493796 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5222. Min Act: -0.1700

Data Index: 7353389 (Open Web Text)

Max Activating Token Index: 32

Text #18

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5203. Min Act: -0.1700

Data Index: 960469 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5079. Min Act: -0.1700

Data Index: 457127 (Open Web Text)

Max Activating Token Index: 33