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

Dataset: Open Web Text

Neuron 2691 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: 1.6774. Min Range: -1.6774

Max Act: 1.6774. Min Act: -0.0458

Data Index: 8457011 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6738. Min Act: -0.0458

Data Index: 859681 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6566. Min Act: -0.0458

Data Index: 5016475 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6427. Min Act: -0.1156

Data Index: 6416810 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6388. Min Act: -0.0458

Data Index: 3988658 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6392. Min Act: -0.0458

Data Index: 4862817 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6224. Min Act: -0.0458

Data Index: 872437 (Open Web Text)

Max Activating Token Index: 1010

Text #7

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6267. Min Act: -0.0755

Data Index: 6412222 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6215. Min Act: -0.0458

Data Index: 8172459 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6221. Min Act: -0.0677

Data Index: 5631770 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6122. Min Act: -0.0458

Data Index: 2281726 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6212. Min Act: -0.0458

Data Index: 4817259 (Open Web Text)

Max Activating Token Index: 171

Text #12

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6114. Min Act: -0.0458

Data Index: 852257 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6196. Min Act: -0.0458

Data Index: 7989355 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6202. Min Act: -0.0458

Data Index: 6427223 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6042. Min Act: -0.0667

Data Index: 3597413 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6098. Min Act: -0.0806

Data Index: 6343917 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6078. Min Act: -0.0458

Data Index: 5399321 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6094. Min Act: -0.0660

Data Index: 5711165 (Open Web Text)

Max Activating Token Index: 161

Text #19

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6035. Min Act: -0.0458

Data Index: 5727296 (Open Web Text)

Max Activating Token Index: 198