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

Dataset: Open Web Text

Neuron 2801 in Layer 4

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: 3.8610. Min Range: -3.8610

Max Act: 3.8610. Min Act: -0.1700

Data Index: 5263902 (Open Web Text)

Max Activating Token Index: 28

Text #1

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7705. Min Act: -0.1700

Data Index: 1626693 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7775. Min Act: -0.1700

Data Index: 8606322 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7435. Min Act: -0.1700

Data Index: 1626677 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7356. Min Act: -0.1700

Data Index: 1626694 (Open Web Text)

Max Activating Token Index: 44

Text #5

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7419. Min Act: -0.1700

Data Index: 7495735 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.6855. Min Act: -0.1700

Data Index: 7074123 (Open Web Text)

Max Activating Token Index: 515

Text #7

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7255. Min Act: -0.1700

Data Index: 7876801 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7023. Min Act: -0.1700

Data Index: 2101019 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7358. Min Act: -0.1700

Data Index: 1626688 (Open Web Text)

Max Activating Token Index: 34

Text #10

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7109. Min Act: -0.1700

Data Index: 7079006 (Open Web Text)

Max Activating Token Index: 963

Text #11

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7263. Min Act: -0.1700

Data Index: 1626692 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7075. Min Act: -0.1700

Data Index: 1626684 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.7075. Min Act: -0.1700

Data Index: 1626691 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.6919. Min Act: -0.1700

Data Index: 3392178 (Open Web Text)

Max Activating Token Index: 558

Text #15

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.6929. Min Act: -0.1700

Data Index: 6017118 (Open Web Text)

Max Activating Token Index: 772

Text #16

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.6684. Min Act: -0.1700

Data Index: 4588592 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.6556. Min Act: -0.1700

Data Index: 1626680 (Open Web Text)

Max Activating Token Index: 72

Text #18

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.6672. Min Act: -0.1700

Data Index: 1626674 (Open Web Text)

Max Activating Token Index: 357

Text #19

Max Range: 3.8610. Min Range: -3.8610

Max Act: 3.6517. Min Act: -0.1700

Data Index: 8456533 (Open Web Text)

Max Activating Token Index: 658