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

Dataset: Open Web Text

Neuron 187 in Layer 2

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: 3.2578. Min Range: -3.2578

Max Act: 3.2578. Min Act: -0.1700

Data Index: 7715480 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.2074. Min Act: -0.1700

Data Index: 8485649 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1892. Min Act: -0.1700

Data Index: 3798506 (Open Web Text)

Max Activating Token Index: 452

Text #3

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1828. Min Act: -0.1700

Data Index: 2874099 (Open Web Text)

Max Activating Token Index: 1018

Text #4

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1685. Min Act: -0.1700

Data Index: 2053340 (Open Web Text)

Max Activating Token Index: 134

Text #5

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1685. Min Act: -0.1700

Data Index: 1303378 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1619. Min Act: -0.1700

Data Index: 6847935 (Open Web Text)

Max Activating Token Index: 454

Text #7

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1588. Min Act: -0.1700

Data Index: 979568 (Open Web Text)

Max Activating Token Index: 519

Text #8

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1570. Min Act: -0.1700

Data Index: 7440923 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1491. Min Act: -0.1700

Data Index: 6061818 (Open Web Text)

Max Activating Token Index: 475

Text #10

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1518. Min Act: -0.1700

Data Index: 6339887 (Open Web Text)

Max Activating Token Index: 713

Text #11

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1499. Min Act: -0.1700

Data Index: 8494851 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1461. Min Act: -0.1700

Data Index: 6888229 (Open Web Text)

Max Activating Token Index: 743

Text #13

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1308. Min Act: -0.1700

Data Index: 6596381 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1348. Min Act: -0.1700

Data Index: 485233 (Open Web Text)

Max Activating Token Index: 710

Text #15

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1348. Min Act: -0.1700

Data Index: 4969671 (Open Web Text)

Max Activating Token Index: 103

Text #16

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1388. Min Act: -0.1700

Data Index: 907323 (Open Web Text)

Max Activating Token Index: 221

Text #17

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1422. Min Act: -0.1700

Data Index: 2165537 (Open Web Text)

Max Activating Token Index: 189

Text #18

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1202. Min Act: -0.1700

Data Index: 968672 (Open Web Text)

Max Activating Token Index: 987

Text #19

Max Range: 3.2578. Min Range: -3.2578

Max Act: 3.1601. Min Act: -0.1700

Data Index: 3075345 (Open Web Text)

Max Activating Token Index: 894