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

Dataset: Open Web Text

Neuron 2237 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: 3.6204. Min Range: -3.6204

Max Act: 3.6124. Min Act: -0.1700

Data Index: 7487028 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.6204. Min Act: -0.1700

Data Index: 8267319 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5708. Min Act: -0.1700

Data Index: 1782507 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5483. Min Act: -0.1700

Data Index: 2940041 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5306. Min Act: -0.1700

Data Index: 7845812 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5173. Min Act: -0.1700

Data Index: 7207046 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5132. Min Act: -0.1700

Data Index: 3157574 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5144. Min Act: -0.1700

Data Index: 6141803 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5112. Min Act: -0.1700

Data Index: 2260121 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5247. Min Act: -0.1700

Data Index: 5779800 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5318. Min Act: -0.1700

Data Index: 1326710 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4794. Min Act: -0.1700

Data Index: 6349931 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4938. Min Act: -0.1700

Data Index: 4794740 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4826. Min Act: -0.1700

Data Index: 2518807 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4664. Min Act: -0.1700

Data Index: 3562543 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4735. Min Act: -0.1700

Data Index: 129503 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4607. Min Act: -0.1700

Data Index: 3605196 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4728. Min Act: -0.1700

Data Index: 2934380 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4717. Min Act: -0.1700

Data Index: 107064 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4749. Min Act: -0.1700

Data Index: 4159209 (Open Web Text)

Max Activating Token Index: 75