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

Dataset: Open Web Text

Neuron 1156 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: 2.9127. Min Range: -2.9127

Max Act: 2.9106. Min Act: -0.1700

Data Index: 788964 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.9127. Min Act: -0.1700

Data Index: 341705 (Open Web Text)

Max Activating Token Index: 500

Text #2

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8887. Min Act: -0.1700

Data Index: 4269903 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8421. Min Act: -0.1700

Data Index: 769314 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8584. Min Act: -0.1700

Data Index: 7817509 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8584. Min Act: -0.1700

Data Index: 5750327 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8658. Min Act: -0.1700

Data Index: 7753658 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8378. Min Act: -0.1700

Data Index: 1944262 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8486. Min Act: -0.1700

Data Index: 8681523 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8277. Min Act: -0.1700

Data Index: 71003 (Open Web Text)

Max Activating Token Index: 758

Text #10

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8008. Min Act: -0.1700

Data Index: 7060799 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8077. Min Act: -0.1700

Data Index: 8681522 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8073. Min Act: -0.1700

Data Index: 45971 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8121. Min Act: -0.1700

Data Index: 1008241 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8057. Min Act: -0.1700

Data Index: 4807183 (Open Web Text)

Max Activating Token Index: 52

Text #15

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8047. Min Act: -0.1700

Data Index: 3530078 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8084. Min Act: -0.1700

Data Index: 6507278 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8094. Min Act: -0.1700

Data Index: 2533170 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8059. Min Act: -0.1700

Data Index: 7917222 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 2.9127. Min Range: -2.9127

Max Act: 2.8031. Min Act: -0.1700

Data Index: 5574900 (Open Web Text)

Max Activating Token Index: 6