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

Dataset: Open Web Text

Neuron 2009 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: 2.0030. Min Range: -2.0030

Max Act: 2.0030. Min Act: -0.1700

Data Index: 5974038 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9385. Min Act: -0.1700

Data Index: 1782148 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8779. Min Act: -0.1700

Data Index: 5857334 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8976. Min Act: -0.1700

Data Index: 1445111 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8786. Min Act: -0.1700

Data Index: 6961788 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8724. Min Act: -0.1700

Data Index: 4200520 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8708. Min Act: -0.1700

Data Index: 3702783 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8747. Min Act: -0.1700

Data Index: 5930910 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8576. Min Act: -0.1700

Data Index: 8699100 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8411. Min Act: -0.1700

Data Index: 161680 (Open Web Text)

Max Activating Token Index: 890

Text #10

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8508. Min Act: -0.1700

Data Index: 2806758 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8500. Min Act: -0.1700

Data Index: 848401 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8387. Min Act: -0.1700

Data Index: 8373115 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8278. Min Act: -0.1700

Data Index: 8025824 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8470. Min Act: -0.1700

Data Index: 1590500 (Open Web Text)

Max Activating Token Index: 39

Text #15

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8495. Min Act: -0.1700

Data Index: 5911915 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8381. Min Act: -0.1700

Data Index: 5335995 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8465. Min Act: -0.1700

Data Index: 2295143 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8136. Min Act: -0.1700

Data Index: 3697260 (Open Web Text)

Max Activating Token Index: 258

Text #19

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.8381. Min Act: -0.1700

Data Index: 1358830 (Open Web Text)

Max Activating Token Index: 216