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

Dataset: Open Web Text

Neuron 1227 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: 4.5053. Min Range: -4.5053

Max Act: 4.4979. Min Act: -0.1700

Data Index: 8442088 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.5035. Min Act: -0.1700

Data Index: 5690033 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.5053. Min Act: -0.1700

Data Index: 938987 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4793. Min Act: -0.1700

Data Index: 8153122 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4564. Min Act: -0.1700

Data Index: 6309444 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4406. Min Act: -0.1700

Data Index: 4806588 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4478. Min Act: -0.1700

Data Index: 5998191 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4361. Min Act: -0.1700

Data Index: 8771046 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4068. Min Act: -0.1700

Data Index: 1225143 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4357. Min Act: -0.1700

Data Index: 2916748 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4309. Min Act: -0.1700

Data Index: 2900078 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4329. Min Act: -0.1700

Data Index: 2845695 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4067. Min Act: -0.1700

Data Index: 6379691 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4080. Min Act: -0.1700

Data Index: 4564163 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4241. Min Act: -0.1700

Data Index: 6461856 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4228. Min Act: -0.1700

Data Index: 1602604 (Open Web Text)

Max Activating Token Index: 90

Text #16

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4207. Min Act: -0.1700

Data Index: 7164700 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4127. Min Act: -0.1700

Data Index: 4737476 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4010. Min Act: -0.1700

Data Index: 5822558 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.4158. Min Act: -0.1700

Data Index: 8312757 (Open Web Text)

Max Activating Token Index: 12