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

Dataset: Open Web Text

Neuron 918 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: 1.1967. Min Range: -1.1967

Max Act: 1.1967. Min Act: -0.1700

Data Index: 1080205 (Open Web Text)

Max Activating Token Index: 171

Text #1

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1966. Min Act: -0.1700

Data Index: 4558087 (Open Web Text)

Max Activating Token Index: 177

Text #2

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1793. Min Act: -0.1700

Data Index: 4738401 (Open Web Text)

Max Activating Token Index: 169

Text #3

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1850. Min Act: -0.1700

Data Index: 2928719 (Open Web Text)

Max Activating Token Index: 172

Text #4

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1739. Min Act: -0.1700

Data Index: 8603966 (Open Web Text)

Max Activating Token Index: 169

Text #5

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1793. Min Act: -0.1700

Data Index: 3027625 (Open Web Text)

Max Activating Token Index: 163

Text #6

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1756. Min Act: -0.1700

Data Index: 1402856 (Open Web Text)

Max Activating Token Index: 166

Text #7

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1749. Min Act: -0.1700

Data Index: 6841072 (Open Web Text)

Max Activating Token Index: 176

Text #8

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1682. Min Act: -0.1700

Data Index: 4116499 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1721. Min Act: -0.1700

Data Index: 8524067 (Open Web Text)

Max Activating Token Index: 158

Text #10

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1646. Min Act: -0.1700

Data Index: 8215648 (Open Web Text)

Max Activating Token Index: 173

Text #11

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1635. Min Act: -0.1700

Data Index: 8115088 (Open Web Text)

Max Activating Token Index: 155

Text #12

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1645. Min Act: -0.1700

Data Index: 2745354 (Open Web Text)

Max Activating Token Index: 166

Text #13

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1615. Min Act: -0.1700

Data Index: 2703435 (Open Web Text)

Max Activating Token Index: 157

Text #14

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1624. Min Act: -0.1700

Data Index: 1683816 (Open Web Text)

Max Activating Token Index: 170

Text #15

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1648. Min Act: -0.1700

Data Index: 1696513 (Open Web Text)

Max Activating Token Index: 154

Text #16

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1707. Min Act: -0.1700

Data Index: 3171228 (Open Web Text)

Max Activating Token Index: 172

Text #17

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1661. Min Act: -0.1700

Data Index: 4926855 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1653. Min Act: -0.1700

Data Index: 3722011 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 1.1967. Min Range: -1.1967

Max Act: 1.1535. Min Act: -0.1700

Data Index: 2030068 (Open Web Text)

Max Activating Token Index: 150