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

Dataset: Open Web Text

Neuron 873 in Layer 5

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: 4.3126. Min Range: -4.3126

Max Act: 4.3096. Min Act: -0.1700

Data Index: 6478275 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 4.3126. Min Range: -4.3126

Max Act: 4.3126. Min Act: -0.1700

Data Index: 2645409 (Open Web Text)

Max Activating Token Index: 987

Text #2

Max Range: 4.3126. Min Range: -4.3126

Max Act: 4.0770. Min Act: -0.1700

Data Index: 4755491 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 4.3126. Min Range: -4.3126

Max Act: 4.0619. Min Act: -0.1700

Data Index: 3326068 (Open Web Text)

Max Activating Token Index: 92

Text #4

Max Range: 4.3126. Min Range: -4.3126

Max Act: 4.0242. Min Act: -0.1700

Data Index: 6938062 (Open Web Text)

Max Activating Token Index: 105

Text #5

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.8973. Min Act: -0.1700

Data Index: 2427333 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.9119. Min Act: -0.1700

Data Index: 8296282 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.8998. Min Act: -0.1700

Data Index: 3055391 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.9039. Min Act: -0.1700

Data Index: 3711426 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.8350. Min Act: -0.1700

Data Index: 6349596 (Open Web Text)

Max Activating Token Index: 897

Text #10

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.8351. Min Act: -0.1700

Data Index: 1841742 (Open Web Text)

Max Activating Token Index: 847

Text #11

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.8591. Min Act: -0.1700

Data Index: 7728216 (Open Web Text)

Max Activating Token Index: 36

Text #12

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.8882. Min Act: -0.1700

Data Index: 1036718 (Open Web Text)

Max Activating Token Index: 808

Text #13

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.7917. Min Act: -0.1700

Data Index: 8636832 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.8175. Min Act: -0.1700

Data Index: 2163650 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.7616. Min Act: -0.1700

Data Index: 2789896 (Open Web Text)

Max Activating Token Index: 744

Text #16

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.7856. Min Act: -0.1700

Data Index: 7959477 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.7787. Min Act: -0.1700

Data Index: 5409987 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.7170. Min Act: -0.1700

Data Index: 3790978 (Open Web Text)

Max Activating Token Index: 944

Text #19

Max Range: 4.3126. Min Range: -4.3126

Max Act: 3.7242. Min Act: -0.1700

Data Index: 6091055 (Open Web Text)

Max Activating Token Index: 479