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

Dataset: Open Web Text

Neuron 2529 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: 1.8377. Min Range: -1.8377

Max Act: 1.8377. Min Act: -0.1693

Data Index: 5261546 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8290. Min Act: -0.1700

Data Index: 924816 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8290. Min Act: -0.1700

Data Index: 4630808 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8290. Min Act: -0.1698

Data Index: 2920625 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8290. Min Act: -0.1689

Data Index: 8595535 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8232. Min Act: -0.1699

Data Index: 7868063 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8204. Min Act: -0.1599

Data Index: 6331963 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8207. Min Act: -0.1699

Data Index: 6507308 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8094. Min Act: -0.1699

Data Index: 6300068 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8086. Min Act: -0.1695

Data Index: 1608815 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8094. Min Act: -0.1700

Data Index: 6526057 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8106. Min Act: -0.1700

Data Index: 2182547 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8130. Min Act: -0.1680

Data Index: 4449445 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.7977. Min Act: -0.1700

Data Index: 3006926 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.7974. Min Act: -0.1690

Data Index: 2016390 (Open Web Text)

Max Activating Token Index: 400

Text #15

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8006. Min Act: -0.1690

Data Index: 795712 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.7968. Min Act: -0.1698

Data Index: 7612443 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.7977. Min Act: -0.1695

Data Index: 3611019 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.7881. Min Act: -0.1700

Data Index: 3639261 (Open Web Text)

Max Activating Token Index: 500

Text #19

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.7997. Min Act: -0.1698

Data Index: 4130948 (Open Web Text)

Max Activating Token Index: 4