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

Dataset: Open Web Text

Neuron 2510 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: 4.5974. Min Range: -4.5974

Max Act: 4.5974. Min Act: -0.1700

Data Index: 1457661 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4628. Min Act: -0.1700

Data Index: 4772362 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4760. Min Act: -0.1700

Data Index: 6420073 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4827. Min Act: -0.1700

Data Index: 4833840 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4613. Min Act: -0.1700

Data Index: 5016572 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4316. Min Act: -0.1700

Data Index: 4310400 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4416. Min Act: -0.1700

Data Index: 2601340 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4259. Min Act: -0.1700

Data Index: 1336713 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4328. Min Act: -0.1700

Data Index: 3048340 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4123. Min Act: -0.1700

Data Index: 7293789 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.3926. Min Act: -0.1700

Data Index: 4002385 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.3926. Min Act: -0.1700

Data Index: 7227828 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.3981. Min Act: -0.1700

Data Index: 2219293 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.3901. Min Act: -0.1700

Data Index: 5547401 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.3979. Min Act: -0.1700

Data Index: 3437934 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.3926. Min Act: -0.1700

Data Index: 5487098 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4009. Min Act: -0.1700

Data Index: 2624136 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.4123. Min Act: -0.1700

Data Index: 4773080 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.3986. Min Act: -0.1700

Data Index: 354648 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.5974. Min Range: -4.5974

Max Act: 4.3878. Min Act: -0.1700

Data Index: 4139747 (Open Web Text)

Max Activating Token Index: 9