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

Dataset: Open Web Text

Neuron 960 in Layer 4

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: 3.1012. Min Range: -3.1012

Max Act: 3.1012. Min Act: -0.1700

Data Index: 7630573 (Open Web Text)

Max Activating Token Index: 524

Text #1

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0536. Min Act: -0.1700

Data Index: 4323774 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0021. Min Act: -0.1700

Data Index: 2718033 (Open Web Text)

Max Activating Token Index: 652

Text #3

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0242. Min Act: -0.1700

Data Index: 2533665 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9923. Min Act: -0.1700

Data Index: 6346289 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9422. Min Act: -0.1700

Data Index: 603161 (Open Web Text)

Max Activating Token Index: 189

Text #6

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9280. Min Act: -0.1700

Data Index: 3687711 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9285. Min Act: -0.1700

Data Index: 5562119 (Open Web Text)

Max Activating Token Index: 965

Text #8

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9101. Min Act: -0.1700

Data Index: 8647588 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9109. Min Act: -0.1700

Data Index: 289879 (Open Web Text)

Max Activating Token Index: 622

Text #10

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9058. Min Act: -0.1700

Data Index: 1093225 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.8722. Min Act: -0.1700

Data Index: 8225761 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.8808. Min Act: -0.1700

Data Index: 73761 (Open Web Text)

Max Activating Token Index: 396

Text #13

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.8953. Min Act: -0.1700

Data Index: 2938098 (Open Web Text)

Max Activating Token Index: 105

Text #14

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.8554. Min Act: -0.1700

Data Index: 4750181 (Open Web Text)

Max Activating Token Index: 577

Text #15

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.8648. Min Act: -0.1700

Data Index: 5262732 (Open Web Text)

Max Activating Token Index: 889

Text #16

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.8562. Min Act: -0.1700

Data Index: 5076008 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.8269. Min Act: -0.1700

Data Index: 996663 (Open Web Text)

Max Activating Token Index: 131

Text #18

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.8174. Min Act: -0.1700

Data Index: 6509889 (Open Web Text)

Max Activating Token Index: 231

Text #19

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.7616. Min Act: -0.1700

Data Index: 6920787 (Open Web Text)

Max Activating Token Index: 409