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

Dataset: Open Web Text

Neuron 101 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: 4.1661. Min Range: -4.1661

Max Act: 4.1661. Min Act: -0.1579

Data Index: 3590944 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.1493. Min Act: -0.1698

Data Index: 827930 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.1304. Min Act: -0.1700

Data Index: 7473878 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.1050. Min Act: -0.1685

Data Index: 145978 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.1266. Min Act: -0.1674

Data Index: 1836039 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.1293. Min Act: -0.1700

Data Index: 3051198 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0729. Min Act: -0.1677

Data Index: 8098327 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0731. Min Act: -0.1700

Data Index: 1895587 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0550. Min Act: -0.1700

Data Index: 3321372 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0408. Min Act: -0.1696

Data Index: 2649309 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0332. Min Act: -0.1692

Data Index: 2081325 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0308. Min Act: -0.1693

Data Index: 5441985 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0630. Min Act: -0.1700

Data Index: 8343119 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0100. Min Act: -0.1699

Data Index: 3092563 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0108. Min Act: -0.1699

Data Index: 7327421 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0180. Min Act: -0.1686

Data Index: 4373165 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0037. Min Act: -0.1691

Data Index: 4945652 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0047. Min Act: -0.1695

Data Index: 5629516 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0150. Min Act: -0.1697

Data Index: 5931374 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.1661. Min Range: -4.1661

Max Act: 4.0109. Min Act: -0.1700

Data Index: 6096884 (Open Web Text)

Max Activating Token Index: 6