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

Dataset: Open Web Text

Neuron 1850 in Layer 1

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: 1.7310. Min Range: -1.7310

Max Act: 1.7310. Min Act: -0.1700

Data Index: 2978747 (Open Web Text)

Max Activating Token Index: 54

Text #1

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7018. Min Act: -0.1700

Data Index: 7393586 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7071. Min Act: -0.1700

Data Index: 674322 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7012. Min Act: -0.1700

Data Index: 5451314 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7047. Min Act: -0.1700

Data Index: 4594290 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6866. Min Act: -0.1700

Data Index: 224321 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6989. Min Act: -0.1700

Data Index: 891893 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6882. Min Act: -0.1700

Data Index: 2827523 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6804. Min Act: -0.1700

Data Index: 5288089 (Open Web Text)

Max Activating Token Index: 54

Text #9

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6840. Min Act: -0.1700

Data Index: 2440044 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6901. Min Act: -0.1699

Data Index: 6022769 (Open Web Text)

Max Activating Token Index: 54

Text #11

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6826. Min Act: -0.1700

Data Index: 706747 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6882. Min Act: -0.1700

Data Index: 2354888 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6903. Min Act: -0.1700

Data Index: 8648237 (Open Web Text)

Max Activating Token Index: 52

Text #14

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6857. Min Act: -0.1700

Data Index: 2325199 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6832. Min Act: -0.1700

Data Index: 6997222 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6650. Min Act: -0.1700

Data Index: 4241953 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6708. Min Act: -0.1699

Data Index: 5121766 (Open Web Text)

Max Activating Token Index: 40

Text #18

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6805. Min Act: -0.1699

Data Index: 5423359 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6782. Min Act: -0.1700

Data Index: 1265675 (Open Web Text)

Max Activating Token Index: 54