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

Dataset: Open Web Text

Neuron 2339 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: 1.9129. Min Range: -1.9129

Max Act: 1.9129. Min Act: -0.1700

Data Index: 2248579 (Open Web Text)

Max Activating Token Index: 180

Text #1

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8798. Min Act: -0.1700

Data Index: 7614878 (Open Web Text)

Max Activating Token Index: 422

Text #2

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8602. Min Act: -0.1698

Data Index: 8715828 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8573. Min Act: -0.1700

Data Index: 1950350 (Open Web Text)

Max Activating Token Index: 64

Text #4

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8525. Min Act: -0.1700

Data Index: 6978302 (Open Web Text)

Max Activating Token Index: 106

Text #5

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8321. Min Act: -0.1700

Data Index: 6182650 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8242. Min Act: -0.1700

Data Index: 2732443 (Open Web Text)

Max Activating Token Index: 261

Text #7

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8191. Min Act: -0.1700

Data Index: 8074789 (Open Web Text)

Max Activating Token Index: 121

Text #8

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8234. Min Act: -0.1700

Data Index: 1584388 (Open Web Text)

Max Activating Token Index: 444

Text #9

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8145. Min Act: -0.1700

Data Index: 7614879 (Open Web Text)

Max Activating Token Index: 281

Text #10

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8051. Min Act: -0.1700

Data Index: 1751094 (Open Web Text)

Max Activating Token Index: 844

Text #11

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8069. Min Act: -0.1700

Data Index: 6874286 (Open Web Text)

Max Activating Token Index: 234

Text #12

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8006. Min Act: -0.1700

Data Index: 8553600 (Open Web Text)

Max Activating Token Index: 105

Text #13

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.8025. Min Act: -0.1700

Data Index: 2658986 (Open Web Text)

Max Activating Token Index: 556

Text #14

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.7853. Min Act: -0.1700

Data Index: 2487746 (Open Web Text)

Max Activating Token Index: 770

Text #15

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.7897. Min Act: -0.1655

Data Index: 6278642 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.7869. Min Act: -0.1700

Data Index: 432858 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.7833. Min Act: -0.1700

Data Index: 8760637 (Open Web Text)

Max Activating Token Index: 667

Text #18

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.7744. Min Act: -0.1700

Data Index: 6988515 (Open Web Text)

Max Activating Token Index: 223

Text #19

Max Range: 1.9129. Min Range: -1.9129

Max Act: 1.7653. Min Act: -0.1700

Data Index: 2518972 (Open Web Text)

Max Activating Token Index: 785