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

Dataset: Open Web Text

Neuron 1600 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: 2.5302. Min Range: -2.5302

Max Act: 2.5302. Min Act: -0.1700

Data Index: 2370013 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.5010. Min Act: -0.1700

Data Index: 1543887 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4947. Min Act: -0.1700

Data Index: 5557594 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4911. Min Act: -0.1700

Data Index: 6071476 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.5019. Min Act: -0.1700

Data Index: 3960322 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.5051. Min Act: -0.1700

Data Index: 7647839 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4783. Min Act: -0.1700

Data Index: 8279691 (Open Web Text)

Max Activating Token Index: 41

Text #7

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4796. Min Act: -0.1700

Data Index: 2014906 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4796. Min Act: -0.1700

Data Index: 8003573 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4697. Min Act: -0.1700

Data Index: 1220936 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4559. Min Act: -0.1700

Data Index: 2313043 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4706. Min Act: -0.1700

Data Index: 4793827 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4619. Min Act: -0.1700

Data Index: 2227065 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4571. Min Act: -0.1700

Data Index: 7301352 (Open Web Text)

Max Activating Token Index: 239

Text #14

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4609. Min Act: -0.1700

Data Index: 7197773 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4658. Min Act: -0.1700

Data Index: 699365 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4622. Min Act: -0.1700

Data Index: 3432814 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4608. Min Act: -0.1700

Data Index: 5474549 (Open Web Text)

Max Activating Token Index: 250

Text #18

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4670. Min Act: -0.1700

Data Index: 5466856 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.5302. Min Range: -2.5302

Max Act: 2.4620. Min Act: -0.1700

Data Index: 1622752 (Open Web Text)

Max Activating Token Index: 345