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

Dataset: Open Web Text

Neuron 1044 in Layer 2

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: 2.9000. Min Range: -2.9000

Max Act: 2.9000. Min Act: -0.1700

Data Index: 4662682 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8584. Min Act: -0.1700

Data Index: 4338272 (Open Web Text)

Max Activating Token Index: 168

Text #2

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8491. Min Act: -0.1700

Data Index: 3838873 (Open Web Text)

Max Activating Token Index: 92

Text #3

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8391. Min Act: -0.1700

Data Index: 5400244 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8153. Min Act: -0.1700

Data Index: 2017112 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8010. Min Act: -0.1700

Data Index: 2573407 (Open Web Text)

Max Activating Token Index: 54

Text #6

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8196. Min Act: -0.1700

Data Index: 4162996 (Open Web Text)

Max Activating Token Index: 41

Text #7

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8123. Min Act: -0.1700

Data Index: 2202043 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8073. Min Act: -0.1700

Data Index: 6066374 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.8070. Min Act: -0.1700

Data Index: 2198950 (Open Web Text)

Max Activating Token Index: 626

Text #10

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7760. Min Act: -0.1700

Data Index: 8824265 (Open Web Text)

Max Activating Token Index: 68

Text #11

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7791. Min Act: -0.1700

Data Index: 8764296 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7767. Min Act: -0.1700

Data Index: 4163001 (Open Web Text)

Max Activating Token Index: 35

Text #13

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7827. Min Act: -0.1700

Data Index: 6848736 (Open Web Text)

Max Activating Token Index: 54

Text #14

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7783. Min Act: -0.1700

Data Index: 4838841 (Open Web Text)

Max Activating Token Index: 102

Text #15

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7820. Min Act: -0.1700

Data Index: 1802018 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7630. Min Act: -0.1700

Data Index: 8355464 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7672. Min Act: -0.1700

Data Index: 8124083 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7646. Min Act: -0.1700

Data Index: 6997511 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 2.9000. Min Range: -2.9000

Max Act: 2.7784. Min Act: -0.1700

Data Index: 6486245 (Open Web Text)

Max Activating Token Index: 18