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

Dataset: Open Web Text

Neuron 1358 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: 1.9138. Min Range: -1.9138

Max Act: 1.9138. Min Act: -0.1700

Data Index: 281558 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8806. Min Act: -0.1700

Data Index: 5018674 (Open Web Text)

Max Activating Token Index: 86

Text #2

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8454. Min Act: -0.1699

Data Index: 2784515 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8640. Min Act: -0.1700

Data Index: 3558441 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8509. Min Act: -0.1700

Data Index: 1485000 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8478. Min Act: -0.1700

Data Index: 8261959 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8206. Min Act: -0.1700

Data Index: 3275896 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8285. Min Act: -0.1700

Data Index: 1414951 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8073. Min Act: -0.1700

Data Index: 3466856 (Open Web Text)

Max Activating Token Index: 542

Text #9

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8048. Min Act: -0.1700

Data Index: 2836008 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.8009. Min Act: -0.1700

Data Index: 4889456 (Open Web Text)

Max Activating Token Index: 712

Text #11

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7991. Min Act: -0.1700

Data Index: 2325190 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7908. Min Act: -0.1700

Data Index: 6502362 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7886. Min Act: -0.1700

Data Index: 5243168 (Open Web Text)

Max Activating Token Index: 270

Text #14

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7896. Min Act: -0.1700

Data Index: 3326202 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7851. Min Act: -0.1700

Data Index: 5741700 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7899. Min Act: -0.1700

Data Index: 8061586 (Open Web Text)

Max Activating Token Index: 592

Text #17

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7877. Min Act: -0.1700

Data Index: 7769533 (Open Web Text)

Max Activating Token Index: 142

Text #18

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7891. Min Act: -0.1700

Data Index: 7457368 (Open Web Text)

Max Activating Token Index: 100

Text #19

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7746. Min Act: -0.1700

Data Index: 7140421 (Open Web Text)

Max Activating Token Index: 113