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

Dataset: Open Web Text

Neuron 2143 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: 4.6146. Min Range: -4.6146

Max Act: 4.6146. Min Act: -0.1700

Data Index: 1897016 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.5974. Min Act: -0.1700

Data Index: 2407745 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.5662. Min Act: -0.1700

Data Index: 7679103 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.5208. Min Act: -0.1700

Data Index: 8197616 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4978. Min Act: -0.1700

Data Index: 408347 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4789. Min Act: -0.1700

Data Index: 3744270 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4644. Min Act: -0.1700

Data Index: 2408249 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4740. Min Act: -0.1700

Data Index: 5293871 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4485. Min Act: -0.1700

Data Index: 5445939 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4801. Min Act: -0.1700

Data Index: 8681960 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4749. Min Act: -0.1700

Data Index: 5561227 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4673. Min Act: -0.1700

Data Index: 6622303 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4779. Min Act: -0.1700

Data Index: 2889736 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4462. Min Act: -0.1700

Data Index: 7416412 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4462. Min Act: -0.1700

Data Index: 8257381 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4382. Min Act: -0.1700

Data Index: 5476680 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4304. Min Act: -0.1700

Data Index: 4053425 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4462. Min Act: -0.1700

Data Index: 3080906 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4047. Min Act: -0.1700

Data Index: 2128425 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.6146. Min Range: -4.6146

Max Act: 4.4117. Min Act: -0.1700

Data Index: 2292694 (Open Web Text)

Max Activating Token Index: 6