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

Dataset: Open Web Text

Neuron 471 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: 1.9097. Min Range: -1.9097

Max Act: 1.9097. Min Act: -0.1700

Data Index: 1794091 (Open Web Text)

Max Activating Token Index: 967

Text #1

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.8557. Min Act: -0.1700

Data Index: 7176548 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.8304. Min Act: -0.1700

Data Index: 5601782 (Open Web Text)

Max Activating Token Index: 130

Text #3

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.8220. Min Act: -0.1700

Data Index: 6896505 (Open Web Text)

Max Activating Token Index: 125

Text #4

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.8236. Min Act: -0.1700

Data Index: 5877228 (Open Web Text)

Max Activating Token Index: 31

Text #5

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7958. Min Act: -0.1700

Data Index: 3896156 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.8008. Min Act: -0.1700

Data Index: 4379214 (Open Web Text)

Max Activating Token Index: 240

Text #7

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7886. Min Act: -0.1700

Data Index: 3858886 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7971. Min Act: -0.1700

Data Index: 2817430 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7840. Min Act: -0.1700

Data Index: 1986658 (Open Web Text)

Max Activating Token Index: 159

Text #10

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7725. Min Act: -0.1700

Data Index: 4298067 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7872. Min Act: -0.1700

Data Index: 7368520 (Open Web Text)

Max Activating Token Index: 820

Text #12

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7769. Min Act: -0.1700

Data Index: 8508265 (Open Web Text)

Max Activating Token Index: 921

Text #13

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7736. Min Act: -0.1700

Data Index: 5130324 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7735. Min Act: -0.1700

Data Index: 6323970 (Open Web Text)

Max Activating Token Index: 712

Text #15

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7711. Min Act: -0.1700

Data Index: 1705410 (Open Web Text)

Max Activating Token Index: 118

Text #16

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7665. Min Act: -0.1700

Data Index: 3066290 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7719. Min Act: -0.1700

Data Index: 6721907 (Open Web Text)

Max Activating Token Index: 322

Text #18

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7708. Min Act: -0.1700

Data Index: 4225715 (Open Web Text)

Max Activating Token Index: 598

Text #19

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.7641. Min Act: -0.1700

Data Index: 1848238 (Open Web Text)

Max Activating Token Index: 754