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

Dataset: Open Web Text

Neuron 344 in Layer 0

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: 1.9448. Min Range: -1.9448

Max Act: 1.9448. Min Act: -0.1698

Data Index: 6103217 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.9277. Min Act: -0.1700

Data Index: 5859783 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.9206. Min Act: -0.1700

Data Index: 3252896 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8950. Min Act: -0.1700

Data Index: 5721256 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.9006. Min Act: -0.1700

Data Index: 8574132 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8931. Min Act: -0.1700

Data Index: 3844459 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8849. Min Act: -0.1700

Data Index: 5749444 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8810. Min Act: -0.1700

Data Index: 5458928 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8722. Min Act: -0.1680

Data Index: 2507980 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8571. Min Act: -0.1697

Data Index: 626445 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8561. Min Act: -0.1683

Data Index: 1581788 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8492. Min Act: -0.1694

Data Index: 8227060 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8472. Min Act: -0.1695

Data Index: 183743 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8467. Min Act: -0.1700

Data Index: 5724034 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8346. Min Act: -0.1700

Data Index: 6829492 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8375. Min Act: -0.1700

Data Index: 4601853 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8327. Min Act: -0.1696

Data Index: 8084397 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8249. Min Act: -0.1700

Data Index: 2258463 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8303. Min Act: -0.1700

Data Index: 4942210 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8254. Min Act: -0.1700

Data Index: 4488525 (Open Web Text)

Max Activating Token Index: 16