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

Dataset: Open Web Text

Neuron 2054 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: 5.7152. Min Range: -5.7152

Max Act: 5.7152. Min Act: -0.1700

Data Index: 8483308 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6746. Min Act: -0.1700

Data Index: 5740039 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6436. Min Act: -0.1700

Data Index: 7583876 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6698. Min Act: -0.1700

Data Index: 6944595 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6260. Min Act: -0.1700

Data Index: 8689260 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6611. Min Act: -0.1700

Data Index: 6674191 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6117. Min Act: -0.1700

Data Index: 4333635 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6009. Min Act: -0.1700

Data Index: 3882152 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6187. Min Act: -0.1700

Data Index: 7008765 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6326. Min Act: -0.1700

Data Index: 3846235 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6221. Min Act: -0.1700

Data Index: 2134404 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6331. Min Act: -0.1700

Data Index: 5776124 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6388. Min Act: -0.1700

Data Index: 8075324 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6078. Min Act: -0.1700

Data Index: 7968601 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6055. Min Act: -0.1700

Data Index: 3283945 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.6250. Min Act: -0.1700

Data Index: 7682440 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.5972. Min Act: -0.1700

Data Index: 2021861 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.5717. Min Act: -0.1700

Data Index: 3686053 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.5911. Min Act: -0.1700

Data Index: 5751352 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.5999. Min Act: -0.1700

Data Index: 1365058 (Open Web Text)

Max Activating Token Index: 4