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

Dataset: Open Web Text

Neuron 2285 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: 1.4670. Min Range: -1.4670

Max Act: 1.4670. Min Act: -0.1677

Data Index: 8214098 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.4402. Min Act: -0.1636

Data Index: 6853078 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.4280. Min Act: -0.1521

Data Index: 6184219 (Open Web Text)

Max Activating Token Index: 1014

Text #3

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.4220. Min Act: -0.1602

Data Index: 2398251 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.4214. Min Act: -0.1700

Data Index: 4091534 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.4079. Min Act: -0.1590

Data Index: 5788201 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.4000. Min Act: -0.1680

Data Index: 7138664 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.4001. Min Act: -0.1694

Data Index: 3740325 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3909. Min Act: -0.1687

Data Index: 7353918 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3875. Min Act: -0.1694

Data Index: 1033303 (Open Web Text)

Max Activating Token Index: 172

Text #10

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3897. Min Act: -0.1699

Data Index: 5409657 (Open Web Text)

Max Activating Token Index: 254

Text #11

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3873. Min Act: -0.1691

Data Index: 570713 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3891. Min Act: -0.1670

Data Index: 5511012 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3860. Min Act: -0.1600

Data Index: 2200621 (Open Web Text)

Max Activating Token Index: 520

Text #14

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3829. Min Act: -0.1643

Data Index: 3565456 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3852. Min Act: -0.1581

Data Index: 782774 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3879. Min Act: -0.1700

Data Index: 2962360 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3948. Min Act: -0.1677

Data Index: 2581872 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3796. Min Act: -0.1686

Data Index: 1120294 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.3812. Min Act: -0.1660

Data Index: 5733933 (Open Web Text)

Max Activating Token Index: 15