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

Dataset: Open Web Text

Neuron 574 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: 4.3150. Min Range: -4.3150

Max Act: 4.3150. Min Act: -0.1700

Data Index: 4837796 (Open Web Text)

Max Activating Token Index: 848

Text #1

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.2991. Min Act: -0.1700

Data Index: 5357188 (Open Web Text)

Max Activating Token Index: 808

Text #2

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.2655. Min Act: -0.1700

Data Index: 8318094 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1907. Min Act: -0.1700

Data Index: 7531760 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.2331. Min Act: -0.1700

Data Index: 2385134 (Open Web Text)

Max Activating Token Index: 622

Text #5

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1920. Min Act: -0.1700

Data Index: 4316688 (Open Web Text)

Max Activating Token Index: 385

Text #6

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.2128. Min Act: -0.1700

Data Index: 4906820 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1847. Min Act: -0.1700

Data Index: 4504482 (Open Web Text)

Max Activating Token Index: 947

Text #8

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.2082. Min Act: -0.1700

Data Index: 5620997 (Open Web Text)

Max Activating Token Index: 891

Text #9

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1995. Min Act: -0.1700

Data Index: 2356083 (Open Web Text)

Max Activating Token Index: 823

Text #10

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1626. Min Act: -0.1700

Data Index: 2467461 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1564. Min Act: -0.1700

Data Index: 1719529 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1698. Min Act: -0.1700

Data Index: 3062811 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1765. Min Act: -0.1700

Data Index: 6157280 (Open Web Text)

Max Activating Token Index: 70

Text #14

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1813. Min Act: -0.1700

Data Index: 6144590 (Open Web Text)

Max Activating Token Index: 947

Text #15

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1748. Min Act: -0.1700

Data Index: 4273094 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1675. Min Act: -0.1700

Data Index: 7608144 (Open Web Text)

Max Activating Token Index: 662

Text #17

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1515. Min Act: -0.1700

Data Index: 3845250 (Open Web Text)

Max Activating Token Index: 712

Text #18

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1605. Min Act: -0.1700

Data Index: 7907471 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 4.3150. Min Range: -4.3150

Max Act: 4.1783. Min Act: -0.1700

Data Index: 5406723 (Open Web Text)

Max Activating Token Index: 330