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

Dataset: Open Web Text

Neuron 1555 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: 3.2050. Min Range: -3.2050

Max Act: 3.2050. Min Act: -0.1700

Data Index: 1033780 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.1506. Min Act: -0.1700

Data Index: 449244 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0488. Min Act: -0.1700

Data Index: 5367537 (Open Web Text)

Max Activating Token Index: 41

Text #3

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0347. Min Act: -0.1700

Data Index: 5618960 (Open Web Text)

Max Activating Token Index: 934

Text #4

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0282. Min Act: -0.1700

Data Index: 5693302 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0204. Min Act: -0.1700

Data Index: 650435 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0090. Min Act: -0.1700

Data Index: 8530977 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0229. Min Act: -0.1699

Data Index: 981321 (Open Web Text)

Max Activating Token Index: 970

Text #8

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0288. Min Act: -0.1700

Data Index: 1362942 (Open Web Text)

Max Activating Token Index: 282

Text #9

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9959. Min Act: -0.1700

Data Index: 2188498 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9957. Min Act: -0.1700

Data Index: 5618961 (Open Web Text)

Max Activating Token Index: 855

Text #11

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9896. Min Act: -0.1700

Data Index: 7939040 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9731. Min Act: -0.1700

Data Index: 7473117 (Open Web Text)

Max Activating Token Index: 677

Text #13

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9781. Min Act: -0.1700

Data Index: 5394520 (Open Web Text)

Max Activating Token Index: 143

Text #14

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9737. Min Act: -0.1700

Data Index: 144733 (Open Web Text)

Max Activating Token Index: 287

Text #15

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9397. Min Act: -0.1700

Data Index: 650436 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9473. Min Act: -0.1700

Data Index: 2395318 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9460. Min Act: -0.1700

Data Index: 3163626 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9247. Min Act: -0.1700

Data Index: 6231824 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9222. Min Act: -0.1700

Data Index: 7022355 (Open Web Text)

Max Activating Token Index: 47