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

Dataset: Open Web Text

Neuron 3033 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: 3.2639. Min Range: -3.2639

Max Act: 3.2639. Min Act: -0.1700

Data Index: 4740652 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.2509. Min Act: -0.1700

Data Index: 4713135 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.2406. Min Act: -0.1700

Data Index: 6498566 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.2414. Min Act: -0.1700

Data Index: 7729313 (Open Web Text)

Max Activating Token Index: 438

Text #4

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.2127. Min Act: -0.1700

Data Index: 5215126 (Open Web Text)

Max Activating Token Index: 173

Text #5

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.2112. Min Act: -0.1700

Data Index: 6250670 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.2080. Min Act: -0.1700

Data Index: 8795877 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.2011. Min Act: -0.1700

Data Index: 1890345 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1798. Min Act: -0.1700

Data Index: 8096604 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1783. Min Act: -0.1700

Data Index: 8194029 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1909. Min Act: -0.1700

Data Index: 3669259 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1909. Min Act: -0.1700

Data Index: 4900640 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1967. Min Act: -0.1700

Data Index: 8435519 (Open Web Text)

Max Activating Token Index: 119

Text #13

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1845. Min Act: -0.1700

Data Index: 4129964 (Open Web Text)

Max Activating Token Index: 119

Text #14

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1932. Min Act: -0.1700

Data Index: 5068854 (Open Web Text)

Max Activating Token Index: 67

Text #15

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1989. Min Act: -0.1700

Data Index: 2997358 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1699. Min Act: -0.1700

Data Index: 1631904 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1731. Min Act: -0.1700

Data Index: 3266452 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1740. Min Act: -0.1700

Data Index: 7662291 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 3.2639. Min Range: -3.2639

Max Act: 3.1536. Min Act: -0.1700

Data Index: 4062591 (Open Web Text)

Max Activating Token Index: 72