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

Dataset: Open Web Text

Neuron 1724 in Layer 6

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: 3.0286. Min Range: -3.0286

Max Act: 3.0286. Min Act: -0.1700

Data Index: 6208287 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8991. Min Act: -0.1700

Data Index: 8147787 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9064. Min Act: -0.1700

Data Index: 1706795 (Open Web Text)

Max Activating Token Index: 658

Text #3

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7743. Min Act: -0.1700

Data Index: 4175908 (Open Web Text)

Max Activating Token Index: 1002

Text #4

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7565. Min Act: -0.1700

Data Index: 2385916 (Open Web Text)

Max Activating Token Index: 271

Text #5

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7522. Min Act: -0.1700

Data Index: 8148908 (Open Web Text)

Max Activating Token Index: 32

Text #6

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7793. Min Act: -0.1700

Data Index: 2080858 (Open Web Text)

Max Activating Token Index: 876

Text #7

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7762. Min Act: -0.1700

Data Index: 5883190 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7409. Min Act: -0.1700

Data Index: 7956999 (Open Web Text)

Max Activating Token Index: 269

Text #9

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7371. Min Act: -0.1700

Data Index: 6679725 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7193. Min Act: -0.1700

Data Index: 2177765 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7214. Min Act: -0.1700

Data Index: 6932876 (Open Web Text)

Max Activating Token Index: 177

Text #12

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.6885. Min Act: -0.1700

Data Index: 6197014 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.7072. Min Act: -0.1700

Data Index: 1321810 (Open Web Text)

Max Activating Token Index: 501

Text #14

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.6955. Min Act: -0.1700

Data Index: 5285734 (Open Web Text)

Max Activating Token Index: 663

Text #15

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.6728. Min Act: -0.1700

Data Index: 5871660 (Open Web Text)

Max Activating Token Index: 856

Text #16

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.6811. Min Act: -0.1700

Data Index: 3274101 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.6702. Min Act: -0.1700

Data Index: 3833930 (Open Web Text)

Max Activating Token Index: 518

Text #18

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.6591. Min Act: -0.1700

Data Index: 453340 (Open Web Text)

Max Activating Token Index: 858

Text #19

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.6699. Min Act: -0.1700

Data Index: 1930193 (Open Web Text)

Max Activating Token Index: 618