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

Dataset: Open Web Text

Neuron 974 in Layer 5

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: 3.5233. Min Range: -3.5233

Max Act: 3.5233. Min Act: -0.1700

Data Index: 4825175 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4955. Min Act: -0.1700

Data Index: 1736304 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4905. Min Act: -0.1700

Data Index: 2243782 (Open Web Text)

Max Activating Token Index: 762

Text #3

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4642. Min Act: -0.1700

Data Index: 1795325 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4644. Min Act: -0.1700

Data Index: 6449279 (Open Web Text)

Max Activating Token Index: 411

Text #5

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4457. Min Act: -0.1700

Data Index: 8154728 (Open Web Text)

Max Activating Token Index: 656

Text #6

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4377. Min Act: -0.1700

Data Index: 1937122 (Open Web Text)

Max Activating Token Index: 104

Text #7

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4476. Min Act: -0.1700

Data Index: 8399624 (Open Web Text)

Max Activating Token Index: 799

Text #8

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4021. Min Act: -0.1700

Data Index: 895502 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4524. Min Act: -0.1700

Data Index: 851956 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4063. Min Act: -0.1700

Data Index: 7267521 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4266. Min Act: -0.1700

Data Index: 5362580 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4194. Min Act: -0.1700

Data Index: 4813845 (Open Web Text)

Max Activating Token Index: 48

Text #13

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.3876. Min Act: -0.1700

Data Index: 3105936 (Open Web Text)

Max Activating Token Index: 105

Text #14

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4032. Min Act: -0.1700

Data Index: 1654780 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.3960. Min Act: -0.1700

Data Index: 1025627 (Open Web Text)

Max Activating Token Index: 397

Text #16

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4164. Min Act: -0.1700

Data Index: 6997742 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.3882. Min Act: -0.1700

Data Index: 7267514 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.4029. Min Act: -0.1700

Data Index: 3136414 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.5233. Min Range: -3.5233

Max Act: 3.3785. Min Act: -0.1700

Data Index: 1232876 (Open Web Text)

Max Activating Token Index: 523