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

Dataset: Open Web Text

Neuron 2722 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: 3.7311. Min Range: -3.7311

Max Act: 3.7311. Min Act: -0.1700

Data Index: 3945248 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6929. Min Act: -0.1700

Data Index: 4357372 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6842. Min Act: -0.1700

Data Index: 5081427 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6855. Min Act: -0.1700

Data Index: 7452052 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6329. Min Act: -0.1700

Data Index: 3945060 (Open Web Text)

Max Activating Token Index: 608

Text #5

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6327. Min Act: -0.1700

Data Index: 604304 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6494. Min Act: -0.1700

Data Index: 1735038 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6321. Min Act: -0.1700

Data Index: 3303354 (Open Web Text)

Max Activating Token Index: 113

Text #8

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6097. Min Act: -0.1700

Data Index: 6735946 (Open Web Text)

Max Activating Token Index: 225

Text #9

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6150. Min Act: -0.1700

Data Index: 5182428 (Open Web Text)

Max Activating Token Index: 279

Text #10

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6244. Min Act: -0.1700

Data Index: 7486994 (Open Web Text)

Max Activating Token Index: 368

Text #11

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6245. Min Act: -0.1700

Data Index: 1606093 (Open Web Text)

Max Activating Token Index: 272

Text #12

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6218. Min Act: -0.1700

Data Index: 4464215 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6063. Min Act: -0.1700

Data Index: 6817616 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6122. Min Act: -0.1700

Data Index: 3072786 (Open Web Text)

Max Activating Token Index: 366

Text #15

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6046. Min Act: -0.1700

Data Index: 2830398 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6256. Min Act: -0.1700

Data Index: 300988 (Open Web Text)

Max Activating Token Index: 984

Text #17

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.5750. Min Act: -0.1700

Data Index: 2415986 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.5851. Min Act: -0.1700

Data Index: 5853660 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 3.7311. Min Range: -3.7311

Max Act: 3.6019. Min Act: -0.1700

Data Index: 6322503 (Open Web Text)

Max Activating Token Index: 133