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

Dataset: Open Web Text

Neuron 2014 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: 4.6556. Min Range: -4.6556

Max Act: 4.6556. Min Act: -0.1700

Data Index: 1984086 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.5692. Min Act: -0.1700

Data Index: 3156902 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.5123. Min Act: -0.1700

Data Index: 7149961 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.5270. Min Act: -0.1700

Data Index: 5958508 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4837. Min Act: -0.1700

Data Index: 7056221 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4818. Min Act: -0.1700

Data Index: 6131106 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4723. Min Act: -0.1700

Data Index: 1016657 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4810. Min Act: -0.1700

Data Index: 6077312 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4894. Min Act: -0.1700

Data Index: 1901866 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4328. Min Act: -0.1700

Data Index: 7307364 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4513. Min Act: -0.1700

Data Index: 2600054 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4414. Min Act: -0.1700

Data Index: 351636 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4385. Min Act: -0.1700

Data Index: 5294811 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4640. Min Act: -0.1700

Data Index: 4521263 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4405. Min Act: -0.1700

Data Index: 3265744 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4453. Min Act: -0.1700

Data Index: 6294784 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4443. Min Act: -0.1700

Data Index: 6871130 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4091. Min Act: -0.1700

Data Index: 2991148 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4273. Min Act: -0.1700

Data Index: 789188 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.6556. Min Range: -4.6556

Max Act: 4.4041. Min Act: -0.1700

Data Index: 1405686 (Open Web Text)

Max Activating Token Index: 4