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

Dataset: Open Web Text

Neuron 1793 in Layer 3

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: 2.1563. Min Range: -2.1563

Max Act: 2.1563. Min Act: -0.1700

Data Index: 3763149 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.1563. Min Range: -2.1563

Max Act: 2.0176. Min Act: -0.1700

Data Index: 2504225 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 2.1563. Min Range: -2.1563

Max Act: 2.0246. Min Act: -0.1700

Data Index: 3880459 (Open Web Text)

Max Activating Token Index: 25

Text #3

Max Range: 2.1563. Min Range: -2.1563

Max Act: 2.0083. Min Act: -0.1699

Data Index: 7918899 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 2.1563. Min Range: -2.1563

Max Act: 2.0087. Min Act: -0.1700

Data Index: 8227565 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.1563. Min Range: -2.1563

Max Act: 2.0143. Min Act: -0.1699

Data Index: 6697987 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9976. Min Act: -0.1695

Data Index: 3028517 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9789. Min Act: -0.1700

Data Index: 7992403 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9725. Min Act: -0.1700

Data Index: 6827863 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9779. Min Act: -0.1700

Data Index: 4882179 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9552. Min Act: -0.1698

Data Index: 5500032 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9574. Min Act: -0.1698

Data Index: 6344005 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9572. Min Act: -0.1700

Data Index: 7406236 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9512. Min Act: -0.1700

Data Index: 6918325 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9550. Min Act: -0.1700

Data Index: 5004132 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9590. Min Act: -0.1694

Data Index: 3340835 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9613. Min Act: -0.1700

Data Index: 2804987 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9527. Min Act: -0.1695

Data Index: 6054840 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9512. Min Act: -0.1700

Data Index: 5746157 (Open Web Text)

Max Activating Token Index: 44

Text #19

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9472. Min Act: -0.1700

Data Index: 1370053 (Open Web Text)

Max Activating Token Index: 9