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

Dataset: Open Web Text

Neuron 1009 in Layer 3

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: 4.5779. Min Range: -4.5779

Max Act: 4.5779. Min Act: -0.1700

Data Index: 4929106 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.5753. Min Act: -0.1700

Data Index: 4192044 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.5179. Min Act: -0.1700

Data Index: 1692203 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4794. Min Act: -0.1700

Data Index: 699293 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4720. Min Act: -0.1700

Data Index: 2496826 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4856. Min Act: -0.1700

Data Index: 6818999 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4522. Min Act: -0.1700

Data Index: 1796501 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4576. Min Act: -0.1700

Data Index: 5169620 (Open Web Text)

Max Activating Token Index: 36

Text #8

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4098. Min Act: -0.1700

Data Index: 3451205 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4325. Min Act: -0.1700

Data Index: 4336775 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4023. Min Act: -0.1700

Data Index: 8509488 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4061. Min Act: -0.1700

Data Index: 6398819 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4248. Min Act: -0.1700

Data Index: 4004098 (Open Web Text)

Max Activating Token Index: 48

Text #13

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.3892. Min Act: -0.1700

Data Index: 7102545 (Open Web Text)

Max Activating Token Index: 25

Text #14

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.3987. Min Act: -0.1700

Data Index: 6560708 (Open Web Text)

Max Activating Token Index: 27

Text #15

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.3881. Min Act: -0.1700

Data Index: 4638984 (Open Web Text)

Max Activating Token Index: 422

Text #16

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.3998. Min Act: -0.1700

Data Index: 3318449 (Open Web Text)

Max Activating Token Index: 35

Text #17

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.3964. Min Act: -0.1700

Data Index: 4818585 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.3898. Min Act: -0.1700

Data Index: 860671 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.3847. Min Act: -0.1700

Data Index: 7191041 (Open Web Text)

Max Activating Token Index: 555