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

Dataset: Open Web Text

Neuron 2657 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: 3.8718. Min Range: -3.8718

Max Act: 3.8718. Min Act: -0.1700

Data Index: 5367549 (Open Web Text)

Max Activating Token Index: 967

Text #1

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8531. Min Act: -0.1700

Data Index: 5122022 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8213. Min Act: -0.1700

Data Index: 5173026 (Open Web Text)

Max Activating Token Index: 211

Text #3

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8355. Min Act: -0.1700

Data Index: 2176520 (Open Web Text)

Max Activating Token Index: 70

Text #4

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7866. Min Act: -0.1700

Data Index: 2505754 (Open Web Text)

Max Activating Token Index: 814

Text #5

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7580. Min Act: -0.1700

Data Index: 2928855 (Open Web Text)

Max Activating Token Index: 96

Text #6

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7695. Min Act: -0.1700

Data Index: 4793672 (Open Web Text)

Max Activating Token Index: 298

Text #7

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7159. Min Act: -0.1700

Data Index: 6876455 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6959. Min Act: -0.1700

Data Index: 7502062 (Open Web Text)

Max Activating Token Index: 934

Text #9

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7006. Min Act: -0.1700

Data Index: 6129705 (Open Web Text)

Max Activating Token Index: 1003

Text #10

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7150. Min Act: -0.1700

Data Index: 5144894 (Open Web Text)

Max Activating Token Index: 471

Text #11

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7329. Min Act: -0.1700

Data Index: 4615641 (Open Web Text)

Max Activating Token Index: 144

Text #12

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7148. Min Act: -0.1700

Data Index: 3368720 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6880. Min Act: -0.1700

Data Index: 3176507 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7032. Min Act: -0.1700

Data Index: 3604136 (Open Web Text)

Max Activating Token Index: 504

Text #15

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7082. Min Act: -0.1700

Data Index: 211809 (Open Web Text)

Max Activating Token Index: 851

Text #16

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6593. Min Act: -0.1700

Data Index: 4910043 (Open Web Text)

Max Activating Token Index: 631

Text #17

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6646. Min Act: -0.1700

Data Index: 1779908 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6626. Min Act: -0.1700

Data Index: 5789440 (Open Web Text)

Max Activating Token Index: 588

Text #19

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6482. Min Act: -0.1700

Data Index: 2935289 (Open Web Text)

Max Activating Token Index: 772