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

Dataset: Open Web Text

Neuron 858 in Layer 5

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: 5.0747. Min Range: -5.0747

Max Act: 5.0747. Min Act: -0.1700

Data Index: 2786896 (Open Web Text)

Max Activating Token Index: 37

Text #1

Max Range: 5.0747. Min Range: -5.0747

Max Act: 5.0160. Min Act: -0.1700

Data Index: 958839 (Open Web Text)

Max Activating Token Index: 627

Text #2

Max Range: 5.0747. Min Range: -5.0747

Max Act: 5.0119. Min Act: -0.1700

Data Index: 5280820 (Open Web Text)

Max Activating Token Index: 824

Text #3

Max Range: 5.0747. Min Range: -5.0747

Max Act: 5.0252. Min Act: -0.1700

Data Index: 6725940 (Open Web Text)

Max Activating Token Index: 734

Text #4

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9946. Min Act: -0.1700

Data Index: 5996230 (Open Web Text)

Max Activating Token Index: 997

Text #5

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9788. Min Act: -0.1700

Data Index: 4524647 (Open Web Text)

Max Activating Token Index: 850

Text #6

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9830. Min Act: -0.1700

Data Index: 1657956 (Open Web Text)

Max Activating Token Index: 783

Text #7

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9769. Min Act: -0.1700

Data Index: 8591794 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 5.0747. Min Range: -5.0747

Max Act: 5.0004. Min Act: -0.1700

Data Index: 8060645 (Open Web Text)

Max Activating Token Index: 868

Text #9

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9879. Min Act: -0.1700

Data Index: 7031463 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9877. Min Act: -0.1700

Data Index: 5705431 (Open Web Text)

Max Activating Token Index: 1013

Text #11

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9810. Min Act: -0.1700

Data Index: 7002438 (Open Web Text)

Max Activating Token Index: 765

Text #12

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9846. Min Act: -0.1700

Data Index: 5586190 (Open Web Text)

Max Activating Token Index: 310

Text #13

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9824. Min Act: -0.1700

Data Index: 51263 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9359. Min Act: -0.1700

Data Index: 4090039 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9376. Min Act: -0.1700

Data Index: 698525 (Open Web Text)

Max Activating Token Index: 974

Text #16

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9553. Min Act: -0.1700

Data Index: 6543156 (Open Web Text)

Max Activating Token Index: 871

Text #17

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9368. Min Act: -0.1700

Data Index: 6995364 (Open Web Text)

Max Activating Token Index: 343

Text #18

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9680. Min Act: -0.1700

Data Index: 2376038 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 5.0747. Min Range: -5.0747

Max Act: 4.9374. Min Act: -0.1700

Data Index: 2490934 (Open Web Text)

Max Activating Token Index: 937