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

Dataset: Open Web Text

Neuron 345 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: 1.9189. Min Range: -1.9189

Max Act: 1.9189. Min Act: -0.1700

Data Index: 5087486 (Open Web Text)

Max Activating Token Index: 118

Text #1

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.9082. Min Act: -0.1700

Data Index: 3989483 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8669. Min Act: -0.1700

Data Index: 8322672 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8629. Min Act: -0.1700

Data Index: 2796121 (Open Web Text)

Max Activating Token Index: 569

Text #4

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8590. Min Act: -0.1700

Data Index: 724326 (Open Web Text)

Max Activating Token Index: 71

Text #5

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8568. Min Act: -0.1700

Data Index: 4583287 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8518. Min Act: -0.1700

Data Index: 8710568 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8501. Min Act: -0.1700

Data Index: 3509051 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8529. Min Act: -0.1700

Data Index: 5742141 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8405. Min Act: -0.1700

Data Index: 8270536 (Open Web Text)

Max Activating Token Index: 231

Text #10

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8230. Min Act: -0.1700

Data Index: 1482648 (Open Web Text)

Max Activating Token Index: 71

Text #11

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8274. Min Act: -0.1700

Data Index: 908428 (Open Web Text)

Max Activating Token Index: 370

Text #12

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8283. Min Act: -0.1700

Data Index: 5889135 (Open Web Text)

Max Activating Token Index: 119

Text #13

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8135. Min Act: -0.1700

Data Index: 1140650 (Open Web Text)

Max Activating Token Index: 179

Text #14

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8190. Min Act: -0.1700

Data Index: 1837716 (Open Web Text)

Max Activating Token Index: 657

Text #15

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8120. Min Act: -0.1700

Data Index: 8557397 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.7975. Min Act: -0.1700

Data Index: 3699678 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8059. Min Act: -0.1700

Data Index: 6534356 (Open Web Text)

Max Activating Token Index: 625

Text #18

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8081. Min Act: -0.1700

Data Index: 254995 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.8107. Min Act: -0.1700

Data Index: 860192 (Open Web Text)

Max Activating Token Index: 796