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

Dataset: Open Web Text

Neuron 1486 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: 1.1328. Min Range: -1.1328

Max Act: 1.1328. Min Act: -0.1700

Data Index: 4932702 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0630. Min Act: -0.1700

Data Index: 2725327 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0453. Min Act: -0.1700

Data Index: 1815895 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0385. Min Act: -0.1700

Data Index: 5909685 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0363. Min Act: -0.1700

Data Index: 743412 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0334. Min Act: -0.1700

Data Index: 3405275 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0191. Min Act: -0.1700

Data Index: 6404679 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0129. Min Act: -0.1700

Data Index: 3269895 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0136. Min Act: -0.1700

Data Index: 3485495 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9967. Min Act: -0.1700

Data Index: 2589982 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9971. Min Act: -0.1700

Data Index: 4488238 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.0012. Min Act: -0.1700

Data Index: 529131 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9924. Min Act: -0.1700

Data Index: 7298897 (Open Web Text)

Max Activating Token Index: 851

Text #13

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9929. Min Act: -0.1700

Data Index: 8424710 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9951. Min Act: -0.1700

Data Index: 5102172 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9954. Min Act: -0.1700

Data Index: 2483236 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9857. Min Act: -0.1700

Data Index: 6735129 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9873. Min Act: -0.1700

Data Index: 4552792 (Open Web Text)

Max Activating Token Index: 895

Text #18

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9889. Min Act: -0.1700

Data Index: 3556724 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9838. Min Act: -0.1700

Data Index: 8516196 (Open Web Text)

Max Activating Token Index: 834