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

Dataset: Open Web Text

Neuron 1013 in Layer 0

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: 0.6196. Min Range: -0.6196

Max Act: 0.6196. Min Act: -0.1700

Data Index: 8613587 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.6098. Min Act: -0.1700

Data Index: 6771496 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5841. Min Act: -0.1700

Data Index: 8374754 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5637. Min Act: -0.1700

Data Index: 8686847 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5536. Min Act: -0.1700

Data Index: 3466138 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5475. Min Act: -0.1700

Data Index: 3767182 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5376. Min Act: -0.1700

Data Index: 6645316 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5270. Min Act: -0.1700

Data Index: 206638 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5306. Min Act: -0.1700

Data Index: 4058803 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5289. Min Act: -0.1700

Data Index: 5759445 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5244. Min Act: -0.1699

Data Index: 6427763 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5128. Min Act: -0.1700

Data Index: 702206 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5199. Min Act: -0.1700

Data Index: 2702485 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4939. Min Act: -0.1700

Data Index: 7578191 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4983. Min Act: -0.1700

Data Index: 3500440 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.5017. Min Act: -0.1700

Data Index: 2964802 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4704. Min Act: -0.1700

Data Index: 4611044 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4832. Min Act: -0.1700

Data Index: 2441662 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4768. Min Act: -0.1700

Data Index: 3074511 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 0.6196. Min Range: -0.6196

Max Act: 0.4694. Min Act: -0.1700

Data Index: 6763698 (Open Web Text)

Max Activating Token Index: 46